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. 105146
    Prev
    Next
    INDEX
    Explanations

    curly braces in code or syntax structures

    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
    isOn
    -0.38
     elog
    -0.36
     into
    -0.35
     Espinoza
    -0.35
    "=>$
    -0.34
     chiến
    -0.34
    "</
    -0.34
    Marzo
    -0.34
     Rö
    -0.34
     aar
    -0.34
    POSITIVE LOGITS
    ({
    0.83
    ftagPool
    0.80
     initComponents
    0.71
     StatefulWidget
    0.71
     disambiguazione
    0.70
     BoxDecoration
    0.69
    ::{
    0.69
     propOrder
    0.68
     ${({
    0.68
     {
    0.68
    Activations Density 0.059%

    No Known Activations