© 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. 20-GEMMASCOPE-RES-65K
    11. 75
    Prev
    Next
    INDEX
    Explanations

    elements related to text and HTML structure

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

    occurrences of text and formatting tags in a document

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

    code, html, and documents

    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
     numberOfRows
    -0.84
    .",
    -0.79
    )"),
    -0.78
    .")
    -0.77
    )");
    -0.75
     invokingState
    -0.75
    Jeografia
    -0.74
    érience
    -0.73
    avadoc
    -0.73
    !")
    -0.70
    POSITIVE LOGITS
    ↵
    0.70
    _
    0.57
    Content
    0.55
    content
    0.54
    0.50
    内容
    0.50
     Content
    0.47
     content
    0.46
    {
    0.46
    ↵↵↵↵↵↵
    0.46
    Activations Density 0.067%

    No Known Activations