© 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. 1833
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and their judicial processing

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

    "case"

    np_acts-logits-general · gemini-2.0-flash

    legal case

    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
    SourceChecksum
    -0.50
    Cyfeiriadau
    -0.47
     purpoſe
    -0.44
    GEBURTSDATUM
    -0.44
     WaitForSeconds
    -0.44
    IBLIO
    -0.43
    vidla
    -0.43
     uſed
    -0.43
    guiente
    -0.43
     automatiques
    -0.43
    POSITIVE LOGITS
     case
    0.63
     involving
    0.62
    case
    0.57
     cases
    0.57
     project
    0.55
    案件
    0.54
     caso
    0.53
     casos
    0.53
     matters
    0.53
     matter
    0.52
    Activations Density 0.792%

    No Known Activations