© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 32262
    Prev
    Next
    INDEX
    Explanations

    symbols, punctuation, and formatting elements in code or structured text

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

    code punctuation and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    #+#
    -0.82
     дописавши
    -0.77
    featureID
    -0.77
     ویکی‌پدی
    -0.76
    цездатний
    -0.74
    AndEndTag
    -0.73
     nakalista
    -0.73
    windowFixed
    -0.72
    parsedMessage
    -0.71
     CURIAM
    -0.70
    POSITIVE LOGITS
     everything
    0.32
     things
    0.32
     всичко
    0.29
     pulse
    0.29
     consciousness
    0.29
     te
    0.29
    ʌ
    0.29
    ัว
    0.28
     wszystko
    0.28
    1
    0.28
    Activations Density 0.029%

    No Known Activations