Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 6430
    Prev
    Next
    INDEX
    Explanations

    terms related to judicial processes and legal standards of review

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

    Legal opinions or judgements

    np_acts-logits-general · gemini-2.0-flash

    court actions and review

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GraphicsUnit
    -0.59
     فع
    -0.59
    évaluateur
    -0.55
     affichés
    -0.54
     Inclusive
    -0.52
    CompilerServices
    -0.52
     appart
    -0.51
    ništ
    -0.49
     amicable
    -0.48
     officially
    -0.48
    POSITIVE LOGITS
     juges
    0.75
     courts
    0.74
     ejus
    0.71
     kysy
    0.65
     judges
    0.62
     Courts
    0.62
    courts
    0.60
    ьогодні
    0.60
    Judges
    0.59
     Gerichte
    0.59
    Activations Density 2.605%

    No Known Activations