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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105146
    Prev
    Next
    INDEX
    Explanations

    questions and calculations related to mathematical concepts and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTEE
    -0.41
     belangrij
    -0.39
    WebServlet
    -0.38
     ModelExpression
    -0.38
    oa̍t
    -0.36
    aarrggbb
    -0.36
    Халык
    -0.36
     HasFactory
    -0.36
    delwed
    -0.35
     AttributeSet
    -0.35
    POSITIVE LOGITS
     Inscrivez
    0.63
     desmotivaciones
    0.50
    lámpara
    0.50
     ویکی‌پدیا
    0.49
     Keuangan
    0.46
     CURIAM
    0.45
     InputDecoration
    0.45
    classmethod
    0.45
    expandindo
    0.45
    tame
    0.44
    Activations Density 0.336%

    No Known Activations