© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 98487
    Prev
    Next
    INDEX
    Explanations

    mentions and discussions of opioid addiction and withdrawal

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

    drug withdrawal symptoms

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     πε
    -0.35
     Acker
    -0.32
     Petersen
    -0.32
    šech
    -0.31
    index
    -0.31
     passent
    -0.30
    hashtags
    -0.30
     bored
    -0.29
    yan
    -0.29
     apolog
    -0.29
    POSITIVE LOGITS
    GraphicsUnit
    0.74
     ſche
    0.74
     juſ
    0.73
    parsedMessage
    0.72
     Reſ
    0.72
     Conſ
    0.71
     purpoſe
    0.69
     abſ
    0.68
     Perſ
    0.67
     ſtate
    0.67
    Activations Density 0.041%

    No Known Activations