© 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 - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 5663
    Prev
    Next
    INDEX
    Explanations

    terms related to searching or browsing through digital content

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

    searching through lists and pages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.84
    featureID
    -0.78
     AssemblyTitle
    -0.77
    SharedDtor
    -0.70
     שוליים
    -0.63
     otomatig
    -0.62
     cherchés
    -0.62
     arşivlendi
    -0.62
     autorytatywna
    -0.61
     CanadaChoose
    -0.60
    POSITIVE LOGITS
     list
    0.71
     lists
    0.70
     archives
    0.68
     pages
    0.67
     catalogs
    0.63
     options
    0.61
     catalogues
    0.60
     listings
    0.58
     menus
    0.58
     rows
    0.54
    Activations Density 0.029%

    No Known Activations