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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14547
    Prev
    Next
    INDEX
    Explanations

    references to legal agreements and compliance with laws

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

    Follows "terms," "law," "order," or "constitution."

    np_acts-logits-general · gemini-2.0-flash

    law terms violation compliance

    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
    ChildScrollView
    -0.58
    istoitu
    -0.56
     Proof
    -0.52
    omock
    -0.52
     positively
    -0.50
    IVEREF
    -0.50
    +#+#
    -0.50
     Projections
    -0.48
     커
    -0.48
     समीक्षक
    -0.47
    POSITIVE LOGITS
     violated
    0.42
     étoit
    0.36
     Eſ
    0.35
     violation
    0.34
    Viol
    0.34
     violations
    0.34
    casila
    0.34
    mybatisplus
    0.33
     ſy
    0.33
     vio
    0.33
    Activations Density 0.491%

    No Known Activations