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

    Neuronpedia

    Jacobian LensNEW
    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. 20645
    Prev
    Next
    INDEX
    Explanations

    legal compliance and procedural adherence within a specific context

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

    properly, carefully, correctly

    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
    
    -0.42
    ohjel
    -0.34
    lots
    -0.34
    ंदीखरीदारी
    -0.33
    complexContent
    -0.33
    extAlignment
    -0.32
    一邊
    -0.32
    azioni
    -0.32
    ilton
    -0.31
    Czytaj
    -0.31
    POSITIVE LOGITS
    ArrowToggle
    0.57
     correctly
    0.56
     properly
    0.54
     carefully
    0.52
     careful
    0.50
    correctly
    0.50
     Properly
    0.50
    properly
    0.49
     adequately
    0.48
     suitably
    0.47
    Activations Density 0.191%

    No Known Activations