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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 184
    Prev
    Next
    INDEX
    Explanations

    brands and types of sugary and alcoholic beverages

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

    Beverage types

    np_acts-logits-general · gemini-2.0-flash

    soft drinks and beverages

    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
    abestanden
    -0.85
     виправивши
    -0.81
    igshid
    -0.76
    HandlerContext
    -0.76
    ArgsConstructor
    -0.73
     estekak
    -0.73
    ImageContext
    -0.69
    Попис
    -0.69
    InputTagHelper
    -0.68
     HasFactory
    -0.67
    POSITIVE LOGITS
     drink
    1.20
     soda
    1.16
     drinks
    1.12
     Coke
    1.10
     beverage
    1.07
     Coca
    1.06
     Pepsi
    1.06
     Cola
    1.01
    Pepsi
    0.97
    drink
    0.97
    Activations Density 0.143%

    No Known Activations