© 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
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 9009
    Prev
    Next
    INDEX
    Explanations

    instances of legal terminology and references to judicial procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recommendations
    -0.42
     ranked
    -0.37
     list
    -0.35
    zval
    -0.35
     most
    -0.34
     only
    -0.33
     ranking
    -0.33
    ,$_
    -0.33
     SEDS
    -0.33
     regularly
    -0.33
    POSITIVE LOGITS
     narrator
    0.98
    Interviewer
    0.97
    Narrator
    0.93
     interviewer
    0.84
    Speaker
    0.83
     announcer
    0.83
     Reporter
    0.82
     Narr
    0.80
     Transcript
    0.80
    Reporter
    0.79
    Activations Density 0.390%

    No Known Activations