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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14513
    Prev
    Next
    INDEX
    Explanations

    mentions of various types of beer and related alcoholic beverages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Accesorios
    -0.49
     Matériau
    -0.47
     Teléfono
    -0.46
     pauvreté
    -0.46
     Grä
    -0.46
     pejabat
    -0.45
    aronder
    -0.45
     Infór
    -0.45
     TELEPHONE
    -0.44
     dignité
    -0.44
    POSITIVE LOGITS
     beer
    0.88
     beers
    0.75
     brewery
    0.74
     brewers
    0.71
     breweries
    0.66
     пиво
    0.66
     brew
    0.65
    Beer
    0.64
     Beer
    0.63
     bière
    0.63
    Activations Density 0.045%

    No Known Activations