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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4679
    Prev
    Next
    INDEX
    Explanations

    various forms and mentions of "style" in relation to design and formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    CSS Styles or formatting

    np_acts-logits-general · gemini-2.0-flash

    style and stylesheets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    WindowConstants
    -0.61
    modelBuilder
    -0.60
    sizeCache
    -0.60
     Réponses
    -0.58
     Paglinawan
    -0.57
    utilisons
    -0.56
    🏻
    -0.54
    牲
    -0.54
     Peña
    -0.52
    bewerken
    -0.52
    POSITIVE LOGITS
    guide
    0.70
    μφωνα
    0.69
    heets
    0.66
    extAlignment
    0.65
    styleType
    0.63
     itſelf
    0.63
    iosync
    0.63
     tê
    0.62
     hidup
    0.62
    setProperty
    0.62
    Activations Density 0.060%

    No Known Activations