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. 21-GEMMASCOPE-RES-16K
    6. 271
    Prev
    Next
    INDEX
    Explanations

    references to types of beer and alcohol consumption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    findpost
    -0.60
    TagMode
    -0.57
    جوايز
    -0.56
     дописавши
    -0.53
    ensitive
    -0.52
     Violin
    -0.51
    ļi
    -0.51
     chiff
    -0.50
     صوتيه
    -0.50
    ValueStyle
    -0.50
    POSITIVE LOGITS
     beer
    1.72
     beers
    1.51
     brewery
    1.47
     brewers
    1.46
     Beer
    1.45
     brewed
    1.45
     breweries
    1.40
     brew
    1.39
    Beer
    1.37
     brewing
    1.37
    Activations Density 0.059%

    No Known Activations