© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 13016
    Prev
    Next
    INDEX
    Explanations

    terms related to alcohol consumption and its effects on health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    patterns and data related to alcohol consumption, medical measurements, and statistical reporting.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    references to alcohol consumption and drinking patterns.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Erreferentziak
    -0.38
    ccional
    -0.36
    cipta
    -0.36
    herz
    -0.34
     Syrie
    -0.34
    Eksterne
    -0.33
    SCAPE
    -0.32
     defaultstate
    -0.32
    flex
    -0.32
    FailureListener
    -0.32
    POSITIVE LOGITS
     alcohol
    2.20
    Alcohol
    2.05
     Alcohol
    2.05
    alcohol
    1.95
     drunk
    1.91
     alcoholic
    1.88
     ALCOHOL
    1.77
     drunken
    1.75
     Alkohol
    1.75
     drunkenness
    1.72
    Activations Density 0.376%

    No Known Activations