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. 4-GEMMASCOPE-RES-16K
    6. 11079
    Prev
    Next
    INDEX
    Explanations

    references to sports games and related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    excellents
    -0.56
    DataAnnotations
    -0.53
    ữu
    -0.52
    foria
    -0.50
    jeno
    -0.50
    larak
    -0.49
    isks
    -0.49
    toast
    -0.48
    jdons
    -0.47
     aanbod
    -0.47
    POSITIVE LOGITS
     game
    1.08
    game
    0.95
     المعيارى
    0.88
     partita
    0.88
    games
    0.87
    GAME
    0.85
     estekak
    0.85
     games
    0.84
     GAME
    0.82
     day
    0.80
    Activations Density 0.139%

    No Known Activations