© 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. 28-GEMMASCOPE-RES-16K
    11. 7973
    Prev
    Next
    INDEX
    Explanations

    terms related to alcohol consumption and its health implications

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

    "alcohol" and its use/consumption

    np_acts-logits-general · gemini-2.0-flash

    alcohol health use consumption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    saraba
    -0.56
     initComponents
    -0.54
    Parcelize
    -0.48
     defaultstate
    -0.46
    avax
    -0.44
    gegen
    -0.44
    potensi
    -0.43
    makeConstraints
    -0.42
     كومونز
    -0.42
    roit
    -0.42
    POSITIVE LOGITS
    Alcohol
    0.98
     Alcohol
    0.98
     alcohol
    0.93
     Alkohol
    0.85
     ALCOHOL
    0.84
     álcool
    0.82
    alcohol
    0.81
     alkohol
    0.80
     Alcoholic
    0.75
    Alco
    0.73
    Activations Density 0.178%

    No Known Activations