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. 10-GEMMASCOPE-RES-16K
    6. 10854
    Prev
    Next
    INDEX
    Explanations

    elements related to regex matching and patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ={};
    -0.56
    woor
    -0.49
    Mux
    -0.49
    หว่าง
    -0.49
     Biro
    -0.49
     Murakami
    -0.48
     late
    -0.48
    Popover
    -0.47
     kapan
    -0.46
    ждународ
    -0.46
    POSITIVE LOGITS
    Hochspringen
    0.76
    AutoScaleMode
    0.75
    Personensuche
    0.73
    ThroughAttribute
    0.68
    awtextra
    0.65
     ویکی‌پدیای
    0.55
    ButterKnife
    0.55
    Viitteet
    0.54
     مشارکت‌کنندگان
    0.54
     voordat
    0.53
    Activations Density 0.592%

    No Known Activations