© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 66012
    Prev
    Next
    INDEX
    Explanations

    references to downloads and installation instructions for software or applications

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

    racing game downloads

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.84
     Мексичка
    -0.82
    MigrationBuilder
    -0.78
     nahilalakip
    -0.77
    IsContent
    -0.68
    UnitTesting
    -0.68
    最快更新
    -0.67
    ArgsConstructor
    -0.65
     AssemblyCulture
    -0.63
    invokeLater
    -0.63
    POSITIVE LOGITS
    scan
    0.30
    Verein
    0.27
     共
    0.27
     description
    0.27
    average
    0.26
     palab
    0.26
     Meeres
    0.26
    ALREADY
    0.26
    before
    0.25
     hayas
    0.25
    Activations Density 0.004%

    No Known Activations