© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102733
    Prev
    Next
    INDEX
    Explanations

    references to governmental investigations and legal inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    setObjectName
    -0.40
    izoen
    -0.36
     always
    -0.36
     siempre
    -0.35
     cappuccio
    -0.34
     textStatus
    -0.34
     Always
    -0.34
     دیکھیے
    -0.33
     ivelany
    -0.33
    หว่าง
    -0.32
    POSITIVE LOGITS
     faſt
    0.64
     ſche
    0.61
     Houſe
    0.60
    MLLoader
    0.60
     ſever
    0.57
     pleaſure
    0.55
    ьаж
    0.54
     itſelf
    0.54
    adaptiveStyles
    0.53
     EconPapers
    0.53
    Activations Density 0.042%

    No Known Activations