© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 52813
    Prev
    Next
    INDEX
    Explanations

    terms related to cannabis and marijuana, particularly in the context of legalization and health

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

    cannabis and marijuana

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ell
    -0.40
    QRect
    -0.39
    inė
    -0.35
    reportError
    -0.35
    MessageWindow
    -0.35
    WithFormat
    -0.35
    trou
    -0.34
     MainPage
    -0.34
     Zh
    -0.34
    OF
    -0.34
    POSITIVE LOGITS
     cannabis
    2.13
     Cannabis
    1.98
    Cannabis
    1.93
    cannabis
    1.77
     marijuana
    1.21
     Marijuana
    1.11
     hemp
    0.95
     cannabin
    0.92
    nabis
    0.89
     marihuana
    0.89
    Activations Density 0.007%

    No Known Activations