© 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. 21021
    Prev
    Next
    INDEX
    Explanations

    phrases related to performance and skill in sports

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

    offensive plays

    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
     ligiloj
    -0.45
     незавершена
    -0.43
    galo
    -0.40
    Filmografie
    -0.39
    meta
    -0.33
    angulaire
    -0.33
     Longitude
    -0.32
    Parcelize
    -0.32
     Contour
    -0.32
     الحره
    -0.32
    POSITIVE LOGITS
     offense
    2.14
     offensive
    2.05
     offensively
    2.02
     offence
    1.87
     Offense
    1.82
     Offensive
    1.69
    offensive
    1.63
    Offensive
    1.63
     offensi
    1.62
     offenses
    1.33
    Activations Density 0.079%

    No Known Activations