© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 414
    Prev
    Next
    INDEX
    Explanations

    links and references to stylesheets or scripts within HTML documents

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

    HTML href attribute

    np_acts-logits-general · gemini-2.0-flash

    orientation and href links

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    LookAnd
    -0.62
    lapsingToolbar
    -0.52
    Хьажоргаш
    -0.51
    Erreferentziak
    -0.51
    Aktualisiert
    -0.49
    Tcl
    -0.48
    verton
    -0.47
    منابع
    -0.46
    Sklici
    -0.44
    او
    -0.44
    POSITIVE LOGITS
     href
    0.98
    href
    0.68
    PerformLayout
    0.68
     لينك
    0.64
    Href
    0.59
     forKey
    0.59
     rel
    0.58
    endpush
    0.58
    QSize
    0.58
    ViewImports
    0.58
    Activations Density 0.066%

    No Known Activations