© 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. 35-GEMMASCOPE-RES-16K
    11. 11725
    Prev
    Next
    INDEX
    Explanations

    legal terminology and phrases related to court processes and proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    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
    -0.64
     nahilalakip
    -0.63
    rungsseite
    -0.62
    ніципалі
    -0.62
     للاسماء
    -0.57
    клопе
    -0.56
    sendLogPayload
    -0.53
    قایناق‌لار
    -0.52
    accio
    -0.51
    Tembelea
    -0.50
    POSITIVE LOGITS
     court
    3.06
     courts
    2.72
     Court
    2.69
    Court
    2.45
    court
    2.44
     COURT
    2.39
     Courts
    2.30
    COURT
    2.19
    courts
    2.13
    Cour
    1.74
    Activations Density 1.629%

    No Known Activations