© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14814
    Prev
    Next
    INDEX
    Explanations

    references to players and their relationships or statuses in a context, likely related to gaming

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

    a "player" object in code

    np_acts-logits-general · gemini-2.0-flash

    player marks and skills

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     Neuf
    -0.52
     Hass
    -0.48
     Wain
    -0.48
     Schmitz
    -0.47
     big
    -0.47
    ]!='
    -0.46
     FINE
    -0.45
     Holtz
    -0.44
    arrête
    -0.43
     fine
    -0.43
    POSITIVE LOGITS
     getPlayer
    1.10
    Player
    0.98
     Player
    0.97
     PLAYER
    0.90
    player
    0.89
     player
    0.86
     Spieler
    0.84
    getPlayer
    0.80
    Athlete
    0.80
     Players
    0.79
    Activations Density 0.067%

    No Known Activations