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. 10-GEMMASCOPE-RES-16K
    6. 15730
    Prev
    Next
    INDEX
    Explanations

    words related to hockey players and their statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endphp
    -0.57
    propTypes
    -0.56
    fendi
    -0.55
    mapStateToProps
    -0.51
    FontOfSize
    -0.50
    FunctionFlags
    -0.50
     Maj
    -0.49
     Tower
    -0.49
    jsxFileName
    -0.49
    dou
    -0.49
    POSITIVE LOGITS
     hockey
    1.05
     Hockey
    0.97
    Hockey
    0.92
    hockey
    0.91
     NHL
    0.77
    oredCriteria
    0.75
     skates
    0.72
     CHAPITRE
    0.67
     skating
    0.66
     patin
    0.65
    Activations Density 0.109%

    No Known Activations