© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3654
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to court proceedings

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

    legal document citations and case references with court case numbers and names.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     repeat
    -0.65
     repeating
    -0.60
     wiederhol
    -0.55
    repeat
    -0.50
     Repeat
    -0.50
    Repeat
    -0.50
    Repeating
    -0.48
     повторя
    -0.48
     repeated
    -0.47
     repeats
    -0.45
    POSITIVE LOGITS
     Michigan
    0.73
    Michigan
    0.71
     Kalamazoo
    0.65
     MI
    0.59
     MICHIGAN
    0.59
     Muske
    0.57
     Lansing
    0.54
    Traverse
    0.53
     Traverse
    0.50
     Mich
    0.50
    Activations Density 0.134%

    No Known Activations