© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 13130
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal conditions and debates

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Legal interpretations and debate

    np_acts-logits-general · gemini-2.0-flash

    legal interpretation and debate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     EconPapers
    -0.56
    
    -0.56
    CodedInputStream
    -0.50
    EndGlobal
    -0.49
     tartalomajánló
    -0.49
    Hochspringen
    -0.49
    RTSC
    -0.48
    indd
    -0.48
     purpoſe
    -0.47
    RUnlock
    -0.46
    POSITIVE LOGITS
     interpretation
    0.61
     precedent
    0.60
     legal
    0.59
     legally
    0.58
     precedents
    0.57
    解釈
    0.57
     interpreta
    0.57
     interpretations
    0.56
     legality
    0.56
     interpret
    0.54
    Activations Density 1.282%

    No Known Activations