© 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. 31-GEMMASCOPE-RES-131K
    11. 84396
    Prev
    Next
    INDEX
    Explanations

    phrases related to methods, effectiveness, and specific scenarios in various contexts

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

    excels or performs well

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tembelea
    -0.39
     INTERESAR
    -0.39
    nextProps
    -0.38
    ChildIndex
    -0.37
     urma
    -0.37
    sizeCache
    -0.36
    Aktualisiert
    -0.36
     enfans
    -0.36
     umgeben
    -0.36
    ViewImports
    -0.36
    POSITIVE LOGITS
     excels
    1.26
     excelled
    1.09
     excel
    1.04
     shines
    0.92
     excell
    0.88
     shine
    0.84
     bril
    0.71
     unggul
    0.69
     brille
    0.69
    excel
    0.68
    Activations Density 0.061%

    No Known Activations