© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 14381
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal decisions and courtroom proceedings

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

    judge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    iertos
    -0.43
     wireType
    -0.42
     potere
    -0.40
    
    -0.40
    Kami
    -0.40
     selamat
    -0.39
    Tôi
    -0.39
     riuscito
    -0.39
     éter
    -0.38
     скоро
    -0.38
    POSITIVE LOGITS
     Judge
    1.38
     judge
    1.28
    Judge
    1.22
     JUDGE
    1.11
    judge
    1.08
     judges
    1.02
     Judges
    0.98
    JUDGE
    0.93
     juez
    0.91
    法官
    0.88
    Activations Density 0.051%

    No Known Activations