© 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. 20-GEMMASCOPE-RES-16K
    11. 11882
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to court proceedings and claims

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

    court decisions and legal proceedings

    np_acts-logits-general · gemini-2.0-flash

    court grants or denies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    PyExc
    -0.65
     forState
    -0.59
    DotNetBar
    -0.54
    ToServer
    -0.52
    ipot
    -0.52
     للمعارف
    -0.49
     springfox
    -0.49
    WebpackPlugin
    -0.48
     Negotiations
    -0.48
     ModelExpression
    -0.48
    POSITIVE LOGITS
     ruling
    1.06
     rulings
    0.89
     orders
    0.88
     ordering
    0.84
     verdict
    0.82
     order
    0.81
     Ruling
    0.81
     ordered
    0.81
     ORDERS
    0.79
     granting
    0.79
    Activations Density 2.268%

    No Known Activations