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

    Neuronpedia

    APICircuit 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. 12-GEMMASCOPE-RES-16K
    6. 9228
    Prev
    Next
    INDEX
    Explanations

    dialogue or conversational expressions indicating agreement or response

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.88
    RegressionTest
    -0.80
     saites
    -0.74
    IsContent
    -0.72
    abyrinth
    -0.72
     BoxFit
    -0.70
     Dodo
    -0.70
     epa
    -0.69
    genheim
    -0.69
    []{"
    -0.69
    POSITIVE LOGITS
     Well
    1.00
    Well
    0.94
     well
    0.73
     WELL
    0.71
     hey
    0.68
     Wells
    0.68
     Ну
    0.64
    well
    0.63
     уж
    0.62
     what
    0.61
    Activations Density 0.033%

    No Known Activations