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. 44142
    Prev
    Next
    INDEX
    Explanations

    code constructs and module imports in JavaScript

    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
    +#+#
    -0.59
    HtmlAttribute
    -0.54
    SharedDtor
    -0.53
    SourceChecksum
    -0.52
     InputDecoration
    -0.52
     AttributeSet
    -0.47
     BoxDecoration
    -0.47
    RectangleBorder
    -0.46
    Diweddarwch
    -0.45
     Dider
    -0.45
    POSITIVE LOGITS
    олові
    0.47
    ionato
    0.46
     resourceCulture
    0.46
    ConstraintMaker
    0.39
     fote
    0.38
    CppCodeGen
    0.38
     nahilalakip
    0.37
     căr
    0.37
     متحده
    0.37
    orological
    0.36
    Activations Density 0.001%

    No Known Activations