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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8801
    Prev
    Next
    INDEX
    Explanations

    references to file paths and lines of code in a programming context

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

    daily, monthly, feminine words

    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
    DockStyle
    -0.76
    Datuak
    -0.74
     ModelExpression
    -0.69
    ArrowToggle
    -0.68
    رشف
    -0.67
    AndroidJUnit
    -0.66
    Personensuche
    -0.64
    WireFormatLite
    -0.64
    mergeFrom
    -0.64
    astify
    -0.60
    POSITIVE LOGITS
     diarias
    0.41
    cionado
    0.40
     orquesta
    0.39
     mensuales
    0.36
     diaria
    0.36
     femininas
    0.35
     déclar
    0.35
     democrática
    0.35
     procédure
    0.35
     mensual
    0.35
    Activations Density 0.030%

    No Known Activations