Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 15897
    Prev
    Next
    INDEX
    Explanations

    phrases related to international relations and cooperation, particularly in the context of political statements and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Statements or opinions being expressed

    np_acts-logits-general · gemini-2.0-flash

    stressed or urged actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PyExc
    -0.68
    脚注の使い方
    -0.59
     accidentally
    -0.57
    المكان
    -0.56
     faktisk
    -0.55
     فريبيس
    -0.55
    şiv
    -0.55
     supposedly
    -0.53
     eingeb
    -0.53
     allegedly
    -0.53
    POSITIVE LOGITS
     stressed
    1.04
     stresses
    0.99
     urged
    0.98
     emphasized
    0.96
     stressing
    0.96
     reiterated
    0.94
     reiter
    0.93
     condemned
    0.93
     urge
    0.93
     underscored
    0.92
    Activations Density 0.190%

    No Known Activations