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. 11-GEMMASCOPE-RES-16K
    6. 13926
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nélk
    -0.43
     meia
    -0.42
     hurtig
    -0.41
     Lagi
    -0.41
    ahin
    -0.40
    ハード
    -0.39
     Hyde
    -0.39
    več
    -0.39
     esetén
    -0.39
    même
    -0.39
    POSITIVE LOGITS
    脚注の使い方
    1.06
    aarrggbb
    1.03
    StructEnd
    0.85
    expandindo
    0.82
     ModelExpression
    0.78
    providedIn
    0.74
    SharedDtor
    0.72
    RTEE
    0.72
     AssemblyTitle
    0.70
     تضيفلها
    0.70
    Activations Density 1.382%

    No Known Activations