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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8363
    Prev
    Next
    INDEX
    Explanations

    programming and syntax elements related to XML, CSS, and JavaScript code 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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Jeografia
    -0.50
    Ход
    -0.50
    pexpr
    -0.49
    laces
    -0.47
    -------------</
    -0.46
    voces
    -0.43
    dsi
    -0.43
    riwal
    -0.43
    istiques
    -0.42
     FetchType
    -0.42
    POSITIVE LOGITS
     дописавши
    0.50
    AnimationsModule
    0.47
    tonode
    0.47
    
    0.45
    oredCriteria
    0.42
     getItemCount
    0.39
    MLLoader
    0.38
    InitVars
    0.37
    BagLayout
    0.37
    interopRequire
    0.35
    Activations Density 1.481%

    No Known Activations