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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 2452
    Prev
    Next
    INDEX
    Explanations

    references to sports achievements and player performance

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

    Soccer teams, leagues, and players

    np_acts-logits-general · gemini-2.0-flash

    youth club sports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Välislingid
    -0.62
    MigrationBuilder
    -0.58
    XmlType
    -0.58
    expandindo
    -0.57
    edoria
    -0.53
     olympiques
    -0.53
    esModule
    -0.52
    toBeDefined
    -0.52
    ConstraintLayout
    -0.51
    +#+#
    -0.51
    POSITIVE LOGITS
     juniors
    0.80
     junior
    0.73
     club
    0.73
     senior
    0.71
     seniors
    0.71
     Juniors
    0.70
    horabuena
    0.69
     Junior
    0.66
    junior
    0.65
     underage
    0.65
    Activations Density 0.179%

    No Known Activations