© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 4846
    Prev
    Next
    INDEX
    Explanations

    topics related to marijuana legalization 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 @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.40
     Stringer
    -0.39
    ziplin
    -0.37
    樊
    -0.37
    vernote
    -0.37
     tacón
    -0.36
    odenal
    -0.36
    ilaian
    -0.36
    borderFill
    -0.36
     esponja
    -0.36
    POSITIVE LOGITS
     cannabis
    1.91
     marijuana
    1.77
     Cannabis
    1.73
    Cannabis
    1.66
     Marijuana
    1.59
    cannabis
    1.58
     cannabin
    1.48
     CBD
    1.47
     THC
    1.45
     hemp
    1.39
    Activations Density 0.148%

    No Known Activations