© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 10162
    Prev
    Next
    INDEX
    Explanations

    references to alcoholic beverages and drink recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wheeled
    -0.41
    itness
    -0.40
     hadas
    -0.40
     injust
    -0.39
    boldmath
    -0.38
    embang
    -0.37
    misa
    -0.37
     vélos
    -0.36
     sièges
    -0.36
    childNodes
    -0.36
    POSITIVE LOGITS
     vodka
    0.82
     Vodka
    0.77
     distillery
    0.72
     whisky
    0.72
     Distillery
    0.69
     alcohol
    0.68
     liqueur
    0.66
     whiskey
    0.63
     gin
    0.63
     liquor
    0.62
    Activations Density 0.202%

    No Known Activations