© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 4987
    Prev
    Next
    INDEX
    Explanations

    terms related to alcohol consumption and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.57
     koffie
    -0.52
    Coffee
    -0.50
     coffee
    -0.49
     Coffee
    -0.49
     Cocktail
    -0.47
    coffee
    -0.47
     COFFEE
    -0.47
    Dish
    -0.46
     Kaffee
    -0.46
    POSITIVE LOGITS
     blackout
    0.77
     buzz
    0.63
     Blackout
    0.63
     hammered
    0.60
     wasted
    0.57
     impaired
    0.57
     tips
    0.57
     impairment
    0.53
     intoxication
    0.53
    buzz
    0.52
    Activations Density 0.264%

    No Known Activations