© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 42616
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or categories, particularly in lists

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    commune in the Charente

    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
    Negative Logits
    ImageContext
    -0.39
    ьажоргаш
    -0.38
    InvalidProtocol
    -0.38
    tonode
    -0.36
    deutig
    -0.36
     ilustracja
    -0.35
     originais
    -0.34
    IANGLES
    -0.34
    ElementException
    -0.34
     hinaus
    -0.34
    POSITIVE LOGITS
    Carriera
    0.62
    matchCondition
    0.61
    әрмәләр
    0.50
     disponibilités
    0.50
    
    0.48
    Manbalar
    0.47
    httphttps
    0.45
    发表于
    0.44
    AddAttribute
    0.44
    homonymie
    0.43
    Activations Density 0.040%

    No Known Activations