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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 7487
    Prev
    Next
    INDEX
    Explanations

    references to citations and references within academic or scientific texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     prisa
    -0.30
     recommandée
    -0.29
    AnchorStyles
    -0.29
     rå
    -0.28
     régimen
    -0.28
     carriera
    -0.27
    destroyAll
    -0.27
     مسئول
    -0.25
     reputación
    -0.24
     industriel
    -0.24
    POSITIVE LOGITS
    windowFixed
    0.85
    EndProject
    0.69
     ProtoMessage
    0.66
     שוליים
    0.65
    titleMargin
    0.64
    MigrationBuilder
    0.62
    DoubleQuotes
    0.62
    astify
    0.60
     kaarangay
    0.59
    PostInfinity
    0.59
    Activations Density 0.385%

    No Known Activations