© 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. 16104
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to court proceedings and rulings

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

    Tokens preceding legal arguments or appeals

    np_acts-logits-general · gemini-2.0-flash

    legal party appeals or contends

    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
    !”.
    -0.65
    ьогодні
    -0.65
    Espèce
    -0.64
    UObject
    -0.60
     Dür
    -0.59
    ”…
    -0.59
    )++;
    -0.57
    …).
    -0.57
    )=>{
    -0.56
     polaire
    -0.56
    POSITIVE LOGITS
    apparently
    0.64
     evidently
    0.59
     apparently
    0.59
     herein
    0.53
    Apparently
    0.52
    CastException
    0.52
     Apparently
    0.49
    0.48
     تضيفلها
    0.48
     twofold
    0.47
    Activations Density 3.754%

    No Known Activations