© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12554
    Prev
    Next
    INDEX
    Explanations

    programming or coding terminology and structure

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

    Code-related keywords ("void", "Table", "Figure", "Is")

    np_acts-logits-general · gemini-2.0-flash

    Is/Does questions or void declarations

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    IUrlHelper
    -0.87
     autorytatywna
    -0.82
    httphttps
    -0.78
    ьаж
    -0.66
    الحياه
    -0.66
     ujednoznacz
    -0.65
     ModelRenderer
    -0.61
    parsedMessage
    -0.61
    NameInMap
    -0.60
    XmlAccessType
    -0.59
    POSITIVE LOGITS
     Jerusalén
    0.42
     religión
    0.40
     elaboración
    0.39
     Moscú
    0.36
     coroa
    0.35
     totalidad
    0.35
     república
    0.34
     herida
    0.34
     silueta
    0.33
     húmedo
    0.33
    Activations Density 1.273%

    No Known Activations