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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 15824
    Prev
    Next
    INDEX
    Explanations

    words related to drinking and beverages, especially alcohol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InlineData
    -0.63
    ArgumentParser
    -0.60
     nén
    -0.58
     lượt
    -0.56
    ताब
    -0.55
    cademia
    -0.53
    ként
    -0.53
    abyrinth
    -0.52
     ớt
    -0.52
    TestingModule
    -0.52
    POSITIVE LOGITS
     drink
    3.81
     drinking
    3.68
     Drink
    3.48
     DRINK
    3.41
    drink
    3.39
    Drink
    3.31
     Drinking
    3.27
    drinking
    3.15
    Drinking
    3.12
     drinks
    3.02
    Activations Density 0.062%

    No Known Activations