© 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. 18-GEMMASCOPE-RES-16K
    6. 4341
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to competitive gaming or sports

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

    "Play" or "Player"

    np_acts-logits-general · gemini-2.0-flash

    play and player contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebVitals
    -0.93
    TestingModule
    -0.83
    IonicModule
    -0.79
    EDEFAULT
    -0.79
    endous
    -0.78
    ])));
    -0.77
    />";
    -0.76
    ]))
    
    -0.75
    gnore
    -0.74
    ANDUM
    -0.74
    POSITIVE LOGITS
     Players
    0.78
     players
    0.73
    players
    0.73
     getPlayer
    0.73
    PLAY
    0.71
    Players
    0.67
     PLAY
    0.65
    oplayer
    0.62
     Play
    0.61
    PLAYER
    0.58
    Activations Density 0.165%

    No Known Activations