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. 69618
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to programming or coding 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
     referrerpolicy
    -0.35
    tinyos
    -0.35
    alors
    -0.35
     Bessel
    -0.35
     Zeitraum
    -0.33
     ansch
    -0.33
     surla
    -0.33
    원
    -0.32
    +:+
    -0.31
    ække
    -0.31
    POSITIVE LOGITS
    aarrggbb
    0.60
    SharedDtor
    0.58
     resourceCulture
    0.56
    outState
    0.54
    bitField
    0.54
    Jeografia
    0.53
     if
    0.52
     Wikimedijinoj
    0.52
    หาก
    0.50
     समीक्षाओं
    0.50
    Activations Density 0.010%

    No Known Activations