© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10681
    Prev
    Next
    INDEX
    Explanations

    mentions of alcoholic beverages, particularly wine and beer

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

    Beverages: beer, tea, wine

    np_acts-logits-general · gemini-2.0-flash

    drinks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    Kenmerken
    -0.54
     beſch
    -0.54
    ellos
    -0.54
    chymal
    -0.53
     parachoque
    -0.52
    期刊论文
    -0.51
    entral
    -0.51
    itemBuilder
    -0.50
    ementara
    -0.49
    ſelben
    -0.49
    POSITIVE LOGITS
     wine
    0.38
     drinks
    0.36
     tea
    0.33
    ImageContext
    0.31
     Numerade
    0.31
     trade
    0.29
    CopyWith
    0.28
    tonsoft
    0.28
     affichés
    0.28
     drink
    0.28
    Activations Density 0.062%

    No Known Activations