© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 72468
    Prev
    Next
    INDEX
    Explanations

    elements indicating null values or absence of data

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

    `null`, `0`, `otherwise`, `nil`, `nothing`

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    jsxFileName
    -0.78
     defaultstate
    -0.77
    
    -0.77
     ब्रेकडाउन
    -0.76
     متعلقه
    -0.75
     propOrder
    -0.75
    Tembelea
    -0.75
    IndentedString
    -0.73
    ConstraintMaker
    -0.73
     disambiguazione
    -0.73
    POSITIVE LOGITS
     aanbied
    0.24
     reunião
    0.22
     igaz
    0.22
    <
    0.21
     <
    0.21
    Quiénes
    0.20
     czo
    0.19
    .
    0.19
     spes
    0.19
     до
    0.19
    Activations Density 0.049%

    No Known Activations