© 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. 79262
    Prev
    Next
    INDEX
    Explanations

    elements related to the identification and selection process in research studies

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

    screening and exclusion criteria

    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
    AndEndTag
    -0.73
     Италијани
    -0.68
     wireType
    -0.65
    reportWebVitals
    -0.54
     himſelf
    -0.51
    KommentareTeilen
    -0.50
     itſelf
    -0.49
    SharedDtor
    -0.48
    出版年
    -0.47
     mixt
    -0.47
    POSITIVE LOGITS
    Demografía
    0.43
     attrition
    0.38
     później
    0.38
     Fewer
    0.37
    Few
    0.34
     یافته
    0.34
     pared
    0.34
     fewer
    0.34
    átka
    0.33
     ditem
    0.33
    Activations Density 0.129%

    No Known Activations