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. 11-GEMMASCOPE-RES-16K
    6. 13336
    Prev
    Next
    INDEX
    Explanations

    references to beer and related beverages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mtrl
    -0.59
    TResult
    -0.57
    anzo
    -0.57
    gouv
    -0.54
     Cont
    -0.52
     Wex
    -0.51
    loren
    -0.51
     cont
    -0.51
    iseaux
    -0.50
    воро
    -0.49
    POSITIVE LOGITS
     beer
    1.85
    Beer
    1.74
     BEER
    1.73
     Beer
    1.67
     beers
    1.59
    beer
    1.58
     brewery
    1.54
     breweries
    1.44
     Brewery
    1.42
     bière
    1.37
    Activations Density 0.154%

    No Known Activations