© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8093
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting within sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Identyfik
    -0.88
    IsContent
    -0.84
    Rujuakan
    -0.78
    []
    -0.74
    ^(@)
    -0.73
    RenderAtEndOf
    -0.71
     ویکی‌پدیا
    -0.70
    $.
    -0.70
    ();)
    -0.68
    AndEndTag
    -0.68
    POSITIVE LOGITS
     crossorigin
    0.52
     toutes
    0.48
    ็จ
    0.47
     ulteriori
    0.46
     proprietario
    0.46
    Sadly
    0.45
     líquidos
    0.45
     supplémentaire
    0.45
     مض
    0.44
     ¡
    0.44
    Activations Density 0.263%

    No Known Activations