© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 47793
    Prev
    Next
    INDEX
    Explanations

    references to claims and legal terminology related to contract disputes

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

    breach of contract claim

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     np
    -0.31
     can
    -0.31
     strong
    -0.29
     wh
    -0.28
     pal
    -0.27
     fantastic
    -0.27
     everything
    -0.26
    گاب
    -0.26
     ع
    -0.26
     https
    -0.26
    POSITIVE LOGITS
     ſans
    0.74
    ſelben
    0.74
     betweenstory
    0.73
    DeleteBehavior
    0.69
    Tembelea
    0.69
     erſt
    0.68
     Normdatei
    0.68
    ſammen
    0.68
     ſind
    0.68
     ब्रेकडाउन
    0.68
    Activations Density 0.685%

    No Known Activations