© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 116762
    Prev
    Next
    INDEX
    Explanations

    references to various types of alcoholic beverages

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Negative Logits
    CHELL
    -0.43
    Att
    -0.41
    InputBorder
    -0.40
    Adapt
    -0.40
    邱
    -0.40
    gnore
    -0.40
     vicin
    -0.39
    Dat
    -0.38
     الحد
    -0.38
    AllowUser
    -0.38
    POSITIVE LOGITS
     Whiskey
    1.23
     whiskey
    1.22
    Whiskey
    1.15
     Whisky
    1.12
     whisky
    1.09
    whiskey
    1.07
    whisky
    0.86
     bourbon
    0.75
     Bourbon
    0.73
    🥃
    0.73
    Activations Density 0.002%

    No Known Activations