© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 15983
    Prev
    Next
    INDEX
    Explanations

    references to marijuana legislation and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     antidesliz
    -0.39
     aveug
    -0.37
    แข
    -0.36
    ziplin
    -0.35
     publier
    -0.33
    borderFill
    -0.33
    cimento
    -0.33
    ilaian
    -0.33
     hidráulica
    -0.33
     alumnos
    -0.32
    POSITIVE LOGITS
     cannabis
    1.70
     Cannabis
    1.54
     marijuana
    1.53
    Cannabis
    1.50
    cannabis
    1.42
     Marijuana
    1.40
     THC
    1.34
     cannabin
    1.32
     CBD
    1.26
     hemp
    1.23
    Activations Density 0.114%

    No Known Activations