© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 2536
    Prev
    Next
    INDEX
    Explanations

    terms and references related to beer and brewing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    beer and breweries

    np_acts-logits-general · gemini-2.0-flash

    beer, brewing, beer-battered

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    findpost
    -0.66
     Cornelia
    -0.51
    Mice
    -0.51
    PageFactory
    -0.50
     chiff
    -0.49
     Solitaire
    -0.49
    HtmlAttribute
    -0.49
     Moff
    -0.49
    TagMode
    -0.48
     civiles
    -0.47
    POSITIVE LOGITS
     beer
    1.49
     brewery
    1.39
     brewed
    1.38
     brewers
    1.36
     brew
    1.35
     beers
    1.32
     brewing
    1.32
     brewer
    1.31
     breweries
    1.29
     Brewing
    1.27
    Activations Density 0.054%

    No Known Activations