© 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
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 12823
    Prev
    Next
    INDEX
    Explanations

    terms related to smoking and its associated health consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     JpaRepository
    -0.47
    IntoConstraints
    -0.43
    Transkript
    -0.39
    abyrinth
    -0.38
    /**
    -0.38
    czki
    -0.38
     Thule
    -0.37
     CreateTagHelper
    -0.36
    czka
    -0.36
     ISNI
    -0.35
    POSITIVE LOGITS
     smoking
    2.25
     smoke
    2.13
     tobacco
    2.09
     smokers
    2.05
     cigarette
    1.98
     Smoking
    1.98
     cigarettes
    1.92
     smoker
    1.89
     Smoke
    1.88
     Tobacco
    1.88
    Activations Density 0.337%

    No Known Activations