© 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. 120525
    Prev
    Next
    INDEX
    Explanations

    technical terms related to the inspection and measurement of defects in materials

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

    defect detection and inspection

    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
    Geografía
    -0.35
    yntaxException
    -0.33
     defaultstate
    -0.33
    Inc
    -0.32
    Sementara
    -0.32
     erklä
    -0.32
     zure
    -0.31
     rounding
    -0.31
     estás
    -0.31
     regulación
    -0.31
    POSITIVE LOGITS
     inspections
    0.64
     inspection
    0.62
    abbix
    0.61
     Inspections
    0.56
     detection
    0.55
    oredCriteria
    0.55
     Inspection
    0.54
    GEBURTSDATUM
    0.54
    inspection
    0.53
     referenties
    0.52
    Activations Density 0.018%

    No Known Activations