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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 14430
    Prev
    Next
    INDEX
    Explanations

    specific software and technological terms associated with computer-aided design (CAD) and engineering

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

    CAD, BIM, and design software

    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
     thức
    -0.35
     queima
    -0.34
    wapV
    -0.32
    AsUp
    -0.32
     חיצוניים
    -0.30
    amp
    -0.29
     pik
    -0.28
    Pyx
    -0.28
     kiện
    -0.27
     drops
    -0.27
    POSITIVE LOGITS
     Autodesk
    0.79
    EndGlobalSection
    0.76
     AutoCAD
    0.71
     CAD
    0.61
     Engineering
    0.58
    CAD
    0.57
    Engineering
    0.56
    Ifc
    0.56
     kasarigan
    0.56
     AttributeSet
    0.55
    Activations Density 0.011%

    No Known Activations