Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 5177
    Prev
    Next
    INDEX
    Explanations

    references to players in gaming contexts

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

    Precedes the word "of" or "trade" after "player"

    np_acts-logits-general · gemini-2.0-flash

    player names

    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
    WebVitals
    -1.35
     مشين
    -1.05
    EDEFAULT
    -1.04
    />";
    -1.00
    }],
    
    -0.98
     /\.
    -0.98
     heapq
    -0.97
    Diweddarwch
    -0.94
    Література
    -0.92
    principalTable
    -0.90
    POSITIVE LOGITS
     players
    0.68
     Players
    0.67
    players
    0.66
    <i>
    0.61
    Players
    0.57
     getPlayer
    0.56
    ka
    0.49
    Unknown
    0.48
     roli
    0.48
    PLAYER
    0.48
    Activations Density 0.082%

    No Known Activations