© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 413
    Prev
    Next
    INDEX
    Explanations

    structured data elements and attributes in code or document formats

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

    Math symbols and equations

    np_acts-logits-general · gemini-2.0-flash

    math and code delimiters

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     queſta
    -0.66
     zoude
    -0.60
     increí
    -0.60
     mauva
    -0.59
     ſont
    -0.59
     plufieurs
    -0.57
     laſſen
    -0.57
     tričko
    -0.56
     stockbild
    -0.54
     devriez
    -0.54
    POSITIVE LOGITS
    endregion
    0.47
    évaluateur
    0.43
    商品説明
    0.40
    جغرافيا
    0.40
     rowspan
    0.36
    }\]
    0.35
     unknownFields
    0.35
    epam
    0.34
    ot
    0.34
     CanadaChoose
    0.33
    Activations Density 0.280%

    No Known Activations