© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 109236
    Prev
    Next
    INDEX
    Explanations

    terms related to the consumption and intake of substances, particularly medications

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

    intake and consumption

    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
    contentLoaded
    -0.71
    sizeCache
    -0.56
    onoi
    -0.56
    AISSEE
    -0.55
    uzzy
    -0.52
    bufio
    -0.50
    inspace
    -0.50
    ölker
    -0.50
    enegger
    -0.49
     Италијани
    -0.49
    POSITIVE LOGITS
    __(/*!
    0.40
     uved
    0.40
     Gebrauch
    0.38
     stos
    0.37
     medication
    0.37
     uży
    0.36
     Penggunaan
    0.36
     prakty
    0.36
     kullan
    0.36
     penggunaan
    0.36
    Activations Density 0.060%

    No Known Activations