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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 64589
    Prev
    Next
    INDEX
    Explanations

    attributes related to table column definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    கம்
    -0.35
    PyTuple
    -0.35
    原
    -0.34
    曲
    -0.34
    mapStateToProps
    -0.33
    SqlDataReader
    -0.33
     graduated
    -0.33
     heißt
    -0.33
    XDECREF
    -0.33
     VizieR
    -0.33
    POSITIVE LOGITS
    ftagPool
    0.57
    WebElementEntity
    0.57
     Chwiliwch
    0.51
     contrôle
    0.48
     control
    0.47
    DockStyle
    0.46
    ConstraintMaker
    0.46
    likace
    0.45
     Control
    0.44
    MigrationBuilder
    0.44
    Activations Density 0.001%

    No Known Activations