© 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. 119
    Prev
    Next
    INDEX
    Explanations

    JavaScript code that involves dynamic content manipulation and function calls

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

    elements related to JavaScript coding and data management

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

    javascript window alerts console

    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
    HomeAsUpEnabled
    -0.51
    setVerticalGroup
    -0.47
    ValueGeneration
    -0.42
    lio
    -0.40
     معد
    -0.39
     ihr
    -0.38
    Revenir
    -0.38
     tế
    -0.38
    endphp
    -0.38
    tipation
    -0.38
    POSITIVE LOGITS
    document
    1.43
     document
    1.41
     window
    1.40
    window
    1.37
    alert
    1.21
     console
    1.08
    console
    1.05
     Window
    1.02
     alert
    1.01
     Document
    1.01
    Activations Density 0.229%

    No Known Activations