© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 8676
    Prev
    Next
    INDEX
    Explanations

    references to alcohol consumption and its effects on behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Moisture
    -0.50
    Viitteet
    -0.49
    ورك
    -0.48
    inchen
    -0.47
     snippetHide
    -0.46
    ündig
    -0.44
    tro
    -0.43
     كره
    -0.43
    yenne
    -0.43
    లాలు
    -0.43
    POSITIVE LOGITS
     drunk
    0.98
     drunken
    0.92
     alcoholic
    0.91
     alcohol
    0.90
     alkoh
    0.89
    drunk
    0.87
    Drunk
    0.86
     booze
    0.83
    alcohol
    0.82
    Alcohol
    0.81
    Activations Density 0.195%

    No Known Activations