© 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. 40500
    Prev
    Next
    INDEX
    Explanations

    mentions of reports, findings, and related official recommendations or announcements

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

    reporting results and findings

    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
     Au
    -0.34
     preen
    -0.31
     Und
    -0.30
    App
    -0.30
    Au
    -0.30
     Du
    -0.30
     "@/
    -0.30
     App
    -0.30
    pat
    -0.29
    Props
    -0.29
    POSITIVE LOGITS
    期刊论文
    0.71
     Administrativna
    0.70
    TypedDataSet
    0.66
    adaptiveStyles
    0.66
     results
    0.66
    最快更新
    0.65
     Ergebnisse
    0.65
    AddTagHelper
    0.65
    पया
    0.64
     findings
    0.62
    Activations Density 0.021%

    No Known Activations