© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13301
    Prev
    Next
    INDEX
    Explanations

    mentions of marijuana and its legal status

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

    marijuana/cannabis

    np_acts-logits-general · gemini-2.0-flash

    marijuana effects

    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
     iron
    -0.34
     asas
    -0.32
     CanadaChoose
    -0.31
     Iron
    -0.30
    Iron
    -0.29
    level
    -0.28
    inter
    -0.27
    sprogramm
    -0.27
     peste
    -0.27
    call
    -0.26
    POSITIVE LOGITS
    cannabis
    0.86
     cannabis
    0.85
    Cannabis
    0.82
     Cannabis
    0.80
     cannabin
    0.79
     THC
    0.77
     marijuana
    0.75
     Marijuana
    0.72
     betweenstory
    0.71
    Canna
    0.70
    Activations Density 0.079%

    No Known Activations