© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3805
    Prev
    Next
    INDEX
    Explanations

    terminology related to legal rights and obligations of trustees and beneficiaries in trust agreements

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

    Legal and law-related contexts

    np_acts-logits-general · gemini-2.0-flash

    legal concepts and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    saraba
    -0.58
    ∮
    -0.52
     clatter
    -0.48
    oneofs
    -0.46
     صوتيه
    -0.45
    blitz
    -0.45
    engue
    -0.45
    quehanna
    -0.44
    phyllum
    -0.44
    trop
    -0.44
    POSITIVE LOGITS
     legal
    0.57
     law
    0.52
     légal
    0.51
     legally
    0.51
     giuri
    0.49
     enforceable
    0.44
     usually
    0.41
     attorney
    0.41
     geldt
    0.41
     depends
    0.40
    Activations Density 1.079%

    No Known Activations