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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 90270
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    tonode
    -0.76
    enderror
    -0.72
    $_['
    -0.71
    DotNetBar
    -0.65
    reportWebVitals
    -0.65
     oprot
    -0.64
    :+:
    -0.64
    queryInterface
    -0.63
    ::_('
    -0.63
    IsMutable
    -0.62
    POSITIVE LOGITS
    AutoField
    0.46
    PrimaryKey
    0.37
     key
    0.32
    principalColumn
    0.31
    key
    0.31
    FDRE
    0.26
     utama
    0.26
     spirituelle
    0.26
    DNA
    0.26
    CrossRef
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.