Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11826
    Prev
    Next
    INDEX
    Explanations

    content related to contests, promotions, and incentives for participation

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

    Prizes, giveaways, and sweepstakes

    np_acts-logits-general · gemini-2.0-flash

    free offers and giveaways

    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
     ThemeData
    -0.66
    RenderAtEndOf
    -0.65
    ThroughAttribute
    -0.65
     فريبيس
    -0.65
    disfraz
    -0.59
    archiviato
    -0.55
    Pautan
    -0.55
     demanding
    -0.54
    queryInterface
    -0.54
     onCancelled
    -0.53
    POSITIVE LOGITS
     free
    0.82
     FREE
    0.75
     access
    0.71
     complimentary
    0.71
     unlimited
    0.71
    FREE
    0.68
     gratuitement
    0.66
     vouchers
    0.65
     gratis
    0.65
     accès
    0.63
    Activations Density 0.149%

    No Known Activations