© 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. 9-GEMMASCOPE-RES-131K
    11. 13634
    Prev
    Next
    INDEX
    Explanations

    references to specific brands of whiskey, particularly Jack Daniels and Johnnie Walker

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    whiskey and rum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    الحياه
    -0.59
    richTextPanel
    -0.52
     lenker
    -0.45
    Tembelea
    -0.43
    傍
    -0.41
     («
    -0.41
    ---*/
    -0.41
    __':
    -0.40
    abestanden
    -0.40
    łach
    -0.40
    POSITIVE LOGITS
     whisky
    0.86
     whiskey
    0.85
     distillery
    0.77
     Whisky
    0.74
    whisky
    0.71
     Whiskey
    0.70
    whiskey
    0.69
     distill
    0.69
     Distillery
    0.68
    Personensuche
    0.66
    Activations Density 0.043%

    No Known Activations