© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10712
    Prev
    Next
    INDEX
    Explanations

    terms related to opioid addiction and treatment

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

    "use," "abuse," or addiction-related terms

    np_acts-logits-general · gemini-2.0-flash

    drug and alcohol addiction

    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
     menem
    -0.33
    ühren
    -0.31
    he
    -0.31
     memen
    -0.30
     dina
    -0.30
    ührung
    -0.29
     насколько
    -0.29
    index
    -0.28
    ginate
    -0.28
    äum
    -0.28
    POSITIVE LOGITS
     addiction
    0.80
    Addiction
    0.80
     addictions
    0.77
     Reſ
    0.75
     Addiction
    0.73
     addicts
    0.72
    +#+
    0.72
     alcoholism
    0.71
     Conſ
    0.69
    featureID
    0.68
    Activations Density 0.267%

    No Known Activations