© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11980
    Prev
    Next
    INDEX
    Explanations

    references to smoke or smoking-related topics

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

    Smoke and smoking

    np_acts-logits-general · gemini-2.0-flash

    smoke and related contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    Geplaatst
    -0.95
    StoryboardSegue
    -0.80
    WebVitals
    -0.79
    yntaxException
    -0.69
    NameInMap
    -0.69
    WireFormatLite
    -0.68
     CreateTagHelper
    -0.67
    Билгалдахарш
    -0.67
     EconPapers
    -0.66
     Abp
    -0.65
    POSITIVE LOGITS
     cigarettes
    0.95
     Smo
    0.80
    Smo
    0.80
     cigars
    0.75
     smoke
    0.73
     smokes
    0.71
    smo
    0.71
     tobacco
    0.71
     smoking
    0.70
     smokers
    0.67
    Activations Density 0.056%

    No Known Activations