© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 103791
    Prev
    Next
    INDEX
    Explanations

    references to images or visual media in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    IsContent
    -0.64
    BagConstraints
    -0.54
    ----</
    -0.52
    LookAnd
    -0.49
     ModelRenderer
    -0.48
    WriteTagHelper
    -0.47
     nonUne
    -0.45
    ngdoc
    -0.44
    ViewFeatures
    -0.44
     吋
    -0.44
    POSITIVE LOGITS
     مشين
    0.58
    oneofs
    0.51
     desierto
    0.44
     فريبيس
    0.44
    неопр
    0.44
    Derbyniad
    0.44
     consultato
    0.43
     marito
    0.42
    互联网档案馆
    0.42
    Hochspringen
    0.42
    Activations Density 0.004%

    No Known Activations