© 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. 20492
    Prev
    Next
    INDEX
    Explanations

    JSON and XML syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    tagHelperRunner
    -0.92
     propOrder
    -0.80
     الحره
    -0.75
    RTLR
    -0.73
     MainAxisSize
    -0.73
    adaptiveStyles
    -0.73
    原始内容存档于
    -0.69
    RTSC
    -0.68
    нгред
    -0.66
     المعيارى
    -0.66
    POSITIVE LOGITS
    주
    0.33
    dshaw
    0.32
     hra
    0.31
    hfill
    0.31
    Edit
    0.31
     onSuccess
    0.29
    ismer
    0.29
    rows
    0.29
    bentar
    0.28
    Options
    0.27
    Activations Density 0.013%

    No Known Activations