© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1840
    Prev
    Next
    INDEX
    Explanations

    terms related to judicial discretion and decision-making in legal contexts

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

    Legal/judicial "discretion" context

    np_acts-logits-general · gemini-2.0-flash

    sound discretion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oprot
    -0.74
    évaluateur
    -0.72
    ########.
    -0.68
     betweenstory
    -0.65
    webElementXpaths
    -0.64
     AssemblyCulture
    -0.62
    ñera
    -0.61
    adaptiveStyles
    -0.58
     समीक्षाओं
    -0.57
     nahilalakip
    -0.57
    POSITIVE LOGITS
     discretion
    1.61
     Discretion
    1.13
     discretionary
    1.01
    cretion
    0.91
     judgement
    0.86
     judgment
    0.85
     Judgement
    0.72
     DISC
    0.68
     discre
    0.67
     Judgment
    0.66
    Activations Density 0.342%

    No Known Activations