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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 3109
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Keep
    -0.55
     couldn
    -0.54
     outta
    -0.53
     awfully
    -0.52
    Gimme
    -0.52
    Frankly
    -0.51
     Balkan
    -0.51
     extra
    -0.50
    asyonu
    -0.50
    Yeah
    -0.50
    POSITIVE LOGITS
    mektedir
    0.85
    aarrggbb
    0.76
    GIVEREF
    0.76
     utafitiHapana
    0.75
    WEBPACK
    0.75
    mıştır
    0.74
    AutoScaleMode
    0.72
    maktadır
    0.72
     goederen
    0.71
     насељу
    0.68
    Activations Density 0.818%

    No Known Activations