© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5687
    Prev
    Next
    INDEX
    Explanations

    phrases related to injuries, especially in a sports context

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

    a "game" or "match"

    np_acts-logits-general · gemini-2.0-flash

    points per game

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    στή
    -0.55
     useRouter
    -0.50
    Saluti
    -0.50
    plit
    -0.46
    urrent
    -0.46
    ]._
    -0.46
     Autorisations
    -0.43
     idén
    -0.43
     Meilleures
    -0.42
    ontas
    -0.42
    POSITIVE LOGITS
     game
    1.42
     games
    1.20
    game
    1.10
     match
    1.06
     jogo
    0.93
     wedstrijd
    0.93
    Game
    0.92
     GAME
    0.91
     Game
    0.91
    games
    0.90
    Activations Density 0.156%

    No Known Activations