© 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-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 9778
    Prev
    Next
    INDEX
    Explanations

    references to champagne and related beverages

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    StoryboardSegue
    -0.57
     bleue
    -0.50
    ArrowToggle
    -0.49
     Reese
    -0.46
    рави
    -0.46
     indigo
    -0.46
     schwar
    -0.46
     marrone
    -0.45
    Географиясе
    -0.44
    الدراسه
    -0.44
    POSITIVE LOGITS
     Champagne
    0.98
     champagne
    0.94
     Brut
    0.87
     bubbly
    0.83
    Champagne
    0.81
     bubbles
    0.78
     Reims
    0.76
     sparkling
    0.75
     Bubbles
    0.75
     Prosec
    0.75
    Activations Density 0.076%

    No Known Activations