© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 23114
    Prev
    Next
    INDEX
    Explanations

    concepts and terms related to mastery and expertise

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

    mastery and skill

    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
     henvisninger
    -0.54
    帖最后由
    -0.53
     Clothes
    -0.50
     PopupWindow
    -0.48
     BoxDecoration
    -0.45
     InputDecoration
    -0.44
     فريبيس
    -0.44
     byg
    -0.44
    Clothes
    -0.43
     FBref
    -0.42
    POSITIVE LOGITS
     mastery
    0.85
     mastered
    0.79
     mastering
    0.78
     dominar
    0.75
     maîtrise
    0.70
     Mastery
    0.68
     proficiency
    0.67
     maî
    0.66
     Mastering
    0.64
     beherr
    0.61
    Activations Density 0.011%

    No Known Activations