© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 86251
    Prev
    Next
    INDEX
    Explanations

    concepts and terms related to regulatory compliance

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

    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-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
    getYear
    -0.59
    bentar
    -0.51
     Vann
    -0.51
    <bos>
    -0.49
    numerusform
    -0.48
    Ras
    -0.48
    <<<<<<<<
    -0.48
    marvin
    -0.47
    jetbrains
    -0.45
    readString
    -0.45
    POSITIVE LOGITS
     compliance
    1.20
     Compliance
    1.18
    Compliance
    1.16
    compliance
    1.10
     Compliant
    0.94
    PLIANCE
    0.91
     comply
    0.90
     compliant
    0.83
    compliant
    0.77
     complying
    0.74
    Activations Density 0.011%

    No Known Activations