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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 92788
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to nanotechnology and material analysis

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

    EDS and XPS analysis

    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
     defaultstate
    -0.69
    تقاوى
    -0.61
    UnitTesting
    -0.60
     initComponents
    -0.58
     חיצוניים
    -0.56
    ValueStyle
    -0.56
    IContainer
    -0.54
    ⟬
    -0.54
    addCriterion
    -0.54
     snippetHide
    -0.52
    POSITIVE LOGITS
    sscanf
    0.49
     scan
    0.48
    scan
    0.47
     ouvriers
    0.47
    Scan
    0.42
    SCAN
    0.42
     metals
    0.40
    sividad
    0.40
    PutPixel
    0.39
     impurities
    0.38
    Activations Density 0.042%

    No Known Activations