© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 2366
    Prev
    Next
    INDEX
    Explanations

    non-lexical tokens or formatting artifacts commonly found in markup languages or code snippets

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

    webElementXpaths, </tr>, </

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    তথ্যসূত্র
    -0.74
    IUrlHelper
    -0.51
    ClientSize
    -0.51
    SourceChecksum
    -0.51
    ribune
    -0.49
    原始内容存档于
    -0.48
    homonymie
    -0.48
    saurus
    -0.48
    verwijspagina
    -0.47
    httphttps
    -0.47
    POSITIVE LOGITS
    webElementXpaths
    0.62
     IFTT
    0.62
    EndProject
    0.62
    writeFieldEnd
    0.61
    </tr>
    0.60
    DoubleQuotes
    0.60
     المعيارى
    0.59
     незавершена
    0.59
    </
    0.57
    ThroughAttribute
    0.55
    Activations Density 0.025%

    No Known Activations