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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 82505
    Prev
    Next
    INDEX
    Explanations

    promotional offers and codes related to products and services

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

    sales and discounts

    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
    OCCURRED
    -0.49
    SourceChecksum
    -0.49
     disambiguazione
    -0.44
     gedrag
    -0.43
     dokumenta
    -0.42
     transfieras
    -0.40
     aprendido
    -0.40
    setVerticalGroup
    -0.40
    TypedDataSet
    -0.39
    Derbyniad
    -0.39
    POSITIVE LOGITS
     discount
    1.95
     discounts
    1.87
     promotions
    1.83
     promotion
    1.77
     promo
    1.70
     discounted
    1.66
     Discount
    1.63
    discount
    1.59
     Promotion
    1.56
     Promo
    1.54
    Activations Density 0.150%

    No Known Activations