© 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. 31-GEMMASCOPE-RES-16K
    11. 5148
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to judicial decisions and discretion

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

    phrases indicating that a decision or judgment is within the discretion or authority of a court or judicial official.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    legal language indicating that a matter is within the discretion or authority of a court, judge, or decision-maker.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    phrases assigning decision-making authority or responsibility to a specific person or body (e.g., that something is left to, rests with, or within the discretion/purview of an authority).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.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
    ualaikum
    -0.53
     الرياضيه
    -0.50
    numerusform
    -0.48
    Gambas
    -0.48
    udahkan
    -0.47
    basti
    -0.46
     Comprometido
    -0.46
    complexContent
    -0.45
    caud
    -0.45
     Wicidata
    -0.43
    POSITIVE LOGITS
     responsibility
    0.81
     onus
    0.73
     entirely
    0.70
     solely
    0.69
     Responsibility
    0.67
     rests
    0.66
     belongs
    0.64
     responsabilidad
    0.64
    responsibility
    0.63
     prerogative
    0.63
    Activations Density 0.531%

    No Known Activations