© 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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 106163
    Prev
    Next
    INDEX
    Explanations

    references to awards and recognitions

    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
     ever
    -0.36
     Ever
    -0.35
     onPostExecute
    -0.34
     onBind
    -0.34
     AssemblyCompany
    -0.33
     ddelweddau
    -0.32
     volk
    -0.32
    我们需要
    -0.31
    Override
    -0.31
     isInitialized
    -0.30
    POSITIVE LOGITS
     ujednoznacz
    0.63
    IntoConstraints
    0.61
    RenderAtEndOf
    0.60
    AndEndTag
    0.57
    HtmlAttribute
    0.57
     CreateTagHelper
    0.55
    makeConstraints
    0.54
    RuleContext
    0.52
     समीक्षाओं
    0.50
    CloseOperation
    0.49
    Activations Density 0.008%

    No Known Activations