© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10415
    Prev
    Next
    INDEX
    Explanations

    references to alcohol consumption and its effects

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

    Referring to alcohol consumption

    np_acts-logits-general · gemini-2.0-flash

    alcohol consumption and drinking

    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
    writeFieldEnd
    -0.61
     onCreateView
    -0.59
    upol
    -0.59
    Magne
    -0.57
     Magneto
    -0.57
     SqlParameter
    -0.57
     بيها
    -0.56
     Agassi
    -0.56
     Mime
    -0.55
     aapt
    -0.54
    POSITIVE LOGITS
     alcohol
    2.44
     drink
    2.18
     drinking
    2.17
     Alcohol
    2.14
     alcoholic
    2.12
    Alcohol
    2.11
    alcohol
    2.09
     booze
    2.07
     drunk
    2.03
     drinks
    2.02
    Activations Density 0.288%

    No Known Activations