© 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. 33-GEMMASCOPE-RES-16K
    11. 8730
    Prev
    Next
    INDEX
    Explanations

    legal terminology and procedural references within court documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -1.02
     فريبيس
    -0.80
    rungsseite
    -0.79
     المعيارى
    -0.77
     nahilalakip
    -0.73
     للاسماء
    -0.71
     ModelExpression
    -0.68
     CreateTagHelper
    -0.68
     Signalez
    -0.65
     disambiguazione
    -0.63
    POSITIVE LOGITS
     court
    3.28
     Court
    2.83
     courts
    2.70
    court
    2.63
     COURT
    2.61
    Court
    2.61
     Courts
    2.31
    COURT
    2.30
    courts
    2.16
     courtroom
    1.95
    Activations Density 0.978%

    No Known Activations