© 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-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 27449
    Prev
    Next
    INDEX
    Explanations

    patterns and elements related to XSL (Extensible Stylesheet Language) syntax

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

    commands are, uses of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -1.05
    saraba
    -0.98
    VersionUID
    -0.98
     nahilalakip
    -0.97
    RectangleBorder
    -0.91
    findpost
    -0.90
    featureID
    -0.89
    twimg
    -0.86
    новништво
    -0.86
    verwijspagina
    -0.85
    POSITIVE LOGITS
    She
    0.46
     *
    0.44
     complex
    0.42
     Bio
    0.42
     text
    0.42
    出了一
    0.41
     lask
    0.40
    着一
    0.40
    tus
    0.40
      
    0.40
    Activations Density 0.028%

    No Known Activations