© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 2269
    Prev
    Next
    INDEX
    Explanations

    phrases related to the cost and purchasing of medication

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

    after questions, commands, or statements

    np_acts-logits-general · gemini-2.0-flash

    buy, delivery, drugs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.85
    lapsingToolbar
    -0.85
    ]='\
    -0.78
    aarrggbb
    -0.76
    LLocation
    -0.75
    parsedMessage
    -0.74
     تضيفلها
    -0.73
    DoubleQuotes
    -0.72
    ponses
    -0.72
    buttonBar
    -0.71
    POSITIVE LOGITS
    best
    0.73
     Best
    0.68
    Best
    0.68
     best
    0.66
    does
    0.62
     Cbd
    0.61
     cbd
    0.60
     does
    0.59
     viata
    0.57
     how
    0.57
    Activations Density 0.034%

    No Known Activations