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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9750
    Prev
    Next
    INDEX
    Explanations

    sentences that describe experiences or situations related to food and dining

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ScopeManager
    -0.64
     références
    -0.55
     bVar
    -0.51
     BoxFit
    -0.50
     entrust
    -0.50
    zzleHttp
    -0.50
    curve
    -0.49
    hotels
    -0.49
    axios
    -0.48
     hote
    -0.48
    POSITIVE LOGITS
    ngdoc
    0.90
    yntaxException
    0.70
     prices
    0.63
     food
    0.63
    LabelTagHelper
    0.61
     personale
    0.61
    oredCriteria
    0.57
    labus
    0.57
     parking
    0.57
    ThroughAttribute
    0.55
    Activations Density 0.028%

    No Known Activations