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. 2412
    Prev
    Next
    INDEX
    Explanations

    references to time periods and durations

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

    "over" or "spread" followed by a preposition or number

    np_acts-logits-general · gemini-2.0-flash

    over and spread/span

    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
     المعيارى
    -0.81
    Rüyada
    -0.74
    setupUi
    -0.71
    mobileqq
    -0.68
     betweenstory
    -0.67
     Waray
    -0.65
    GraphicsUnit
    -0.64
     linkovi
    -0.64
     مرئيه
    -0.62
    LookAnd
    -0.62
    POSITIVE LOGITS
     spread
    1.30
     over
    1.24
     Spread
    1.11
    spread
    0.94
    Spread
    0.93
    over
    0.93
     spreads
    0.89
     Over
    0.88
     span
    0.87
     spanning
    0.85
    Activations Density 0.316%

    No Known Activations