© 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. 31-GEMMASCOPE-RES-131K
    11. 70982
    Prev
    Next
    INDEX
    Explanations

    information related to drug safety and usage guidelines

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

    INDICATIONS AND USAGE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bershka
    -0.53
    Organisation
    -0.49
     analysed
    -0.47
     moschino
    -0.47
     analyse
    -0.47
    COLOUR
    -0.46
    Defence
    -0.44
     metadata
    -0.44
     Organisations
    -0.44
    aluminium
    -0.43
    POSITIVE LOGITS
     Signalez
    0.56
    richTextPanel
    0.54
     mergeFrom
    0.54
    存于互联网档案馆
    0.53
    verifyException
    0.52
    Tembelea
    0.52
    AsUp
    0.50
    InitVars
    0.49
    NameInMap
    0.48
    RenderAtEndOf
    0.47
    Activations Density 0.003%

    No Known Activations