© 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. 81831
    Prev
    Next
    INDEX
    Explanations

    mentions of coaching roles in sports

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

    coach or assistant roles

    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
    Cmd
    -0.31
     Gerichte
    -0.30
    runApp
    -0.29
     Maske
    -0.29
    期刊论文
    -0.29
     rentrée
    -0.27
    angulaire
    -0.27
     wł
    -0.27
    ाउन
    -0.27
    gameserver
    -0.27
    POSITIVE LOGITS
     assistant
    1.13
    assistant
    1.05
    Assistant
    1.03
     Assistant
    1.02
     assistants
    0.93
     ASSISTANT
    0.88
     Assistants
    0.86
    ASSIST
    0.82
     assistente
    0.79
     coaching
    0.76
    Activations Density 0.021%

    No Known Activations