© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 8036
    Prev
    Next
    INDEX
    Explanations

    references to tobacco-related issues and smoking behaviors

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

    Cigarette smoking and tobacco-related terms

    np_acts-logits-general · gemini-2.0-flash

    cigarette smoking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.86
    GenerationType
    -0.72
    VolleyError
    -0.69
    WebElementEntity
    -0.67
    XmlAccessType
    -0.67
    })();
    -0.66
     bezeichneter
    -0.65
    pperware
    -0.64
     feldspar
    -0.64
    Hozzáférés
    -0.63
    POSITIVE LOGITS
     smoking
    1.71
     tobacco
    1.71
     smokers
    1.69
     cigarette
    1.65
     cigarettes
    1.58
     Smoking
    1.55
     smoker
    1.54
     Tobacco
    1.52
     nicotine
    1.48
    Tobacco
    1.44
    Activations Density 0.182%

    No Known Activations