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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 54475
    Prev
    Next
    INDEX
    Explanations

    references to various racket sports, particularly tennis and badminton

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

    racket sports and tournaments

    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
     ujednoznacz
    -0.57
    jspx
    -0.56
    Manbalar
    -0.51
    WEBPACK
    -0.50
    NewGuid
    -0.49
     AspNetCore
    -0.46
    uscita
    -0.46
    bertura
    -0.46
    UrlResolution
    -0.46
     berätt
    -0.45
    POSITIVE LOGITS
     tennis
    0.96
     Tennis
    0.85
    Tennis
    0.81
    tennis
    0.78
     badminton
    0.76
    minton
    0.75
     Badminton
    0.72
     racket
    0.70
    🎾
    0.64
     tenis
    0.61
    Activations Density 0.007%

    No Known Activations