© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15057
    Prev
    Next
    INDEX
    Explanations

    terms related to tobacco use and cessation efforts

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

    cigarette smoking/tobacco use

    np_acts-logits-general · gemini-2.0-flash

    smoking and tobacco use cessation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pracę
    -0.35
     ISNI
    -0.34
     cervello
    -0.32
     tâches
    -0.32
     ú
    -0.31
     erwarten
    -0.31
     ciebie
    -0.31
     bangun
    -0.31
    ค่า
    -0.30
    łaszcza
    -0.30
    POSITIVE LOGITS
     cigarettes
    1.12
     smokers
    1.10
     cigarette
    1.10
     tobacco
    1.09
     Tobacco
    1.08
    Tobacco
    1.03
     smoking
    1.02
     Smoking
    1.01
     smoker
    1.00
     Cigarette
    0.97
    Activations Density 0.154%

    No Known Activations