© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 74907
    Prev
    Next
    INDEX
    Explanations

    terms related to various stages of preparation and conditioning in scientific experiments

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

    before procedures or events

    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
    tanleria
    -0.65
    MessageOf
    -0.64
    SourceChecksum
    -0.53
    ToBounds
    -0.52
    bootstrapcdn
    -0.52
    StructEnd
    -0.52
     ligiloj
    -0.50
    onOptions
    -0.48
    WidgetItem
    -0.45
     ویکی‌پدیا
    -0.45
    POSITIVE LOGITS
     preseason
    0.82
     Pre
    0.79
     pre
    0.79
    Pre
    0.75
     precon
    0.72
    PreExecute
    0.70
     PRE
    0.70
    Preheat
    0.68
     preload
    0.68
    preload
    0.67
    Activations Density 0.023%

    No Known Activations