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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 51721
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and programming-related syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    mybatisplus
    -0.40
    Adapted
    -0.39
    ítima
    -0.38
    rshire
    -0.37
     llorar
    -0.36
    GeoNames
    -0.36
     návště
    -0.36
    SECONDARY
    -0.35
    posób
    -0.35
    secondary
    -0.35
    POSITIVE LOGITS
    
    0.54
    PostInfinity
    0.54
    IsMutable
    0.52
    المناصب
    0.52
    __*/
    0.49
     Taktlose
    0.46
     wireType
    0.46
    tilor
    0.45
    IntoConstraints
    0.45
    Hochspringen
    0.45
    Activations Density 0.468%

    No Known Activations