© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 38277
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to law and factual issues being reviewed in a judicial context

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

    legal, factual, objective analysis

    np_acts-logits-general · gemini-2.5-flash-lite

    legal discussion of standards of review—phrases contrasting questions of law and fact (de novo, standard of review, jurisdiction, etc.).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FieldBuilder
    -0.46
     Wikimedijinoj
    -0.46
     flexibilidad
    -0.45
     desierto
    -0.43
     estekak
    -0.42
    SharedDtor
    -0.42
     дописавши
    -0.42
    تقاوى
    -0.41
     незавершена
    -0.40
    NameInMap
    -0.40
    POSITIVE LOGITS
     autorytatywna
    0.64
     factual
    0.52
     XCTest
    0.44
    historical
    0.43
    Hentet
    0.43
     useStyles
    0.42
     evid
    0.41
     science
    0.41
     objective
    0.41
     mathematical
    0.41
    Activations Density 0.192%

    No Known Activations