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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 103136
    Prev
    Next
    INDEX
    Explanations

    elements related to CSS styling in web development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    JspWriter
    -0.65
     utafitiHapana
    -0.62
    AsUp
    -0.57
    TagMode
    -0.57
    findpost
    -0.57
    évaluateur
    -0.56
     ModelExpression
    -0.56
    kloped
    -0.55
    jooq
    -0.53
    awaiter
    -0.50
    POSITIVE LOGITS
    styleUrls
    1.44
     StyleSheet
    0.50
    scss
    0.46
     makeStyles
    0.43
    setStyleSheet
    0.39
    GeoNames
    0.39
    záll
    0.39
     layouts
    0.38
    css
    0.37
    styles
    0.37
    Activations Density 0.000%

    No Known Activations