© 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. 22-GEMMASCOPE-RES-16K
    11. 9968
    Prev
    Next
    INDEX
    Explanations

    elements related to highlighting and emphasizing information in text

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

    Text formatting: bold, italics, highlighting

    np_acts-logits-general · gemini-2.0-flash

    highlighted or emphasized text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.67
    principalColumn
    -0.63
    principalTable
    -0.57
    imageio
    -0.56
    DOCTYPE
    -0.55
    setPref
    -0.54
    يمي
    -0.49
    ENODEV
    -0.49
    Hauptartikel
    -0.48
     poire
    -0.46
    POSITIVE LOGITS
     highlight
    1.60
     highlighted
    1.58
     highlighting
    1.52
     Highlight
    1.50
     underlined
    1.48
     highlights
    1.42
    highlight
    1.38
     underline
    1.34
    Highlight
    1.30
     emphasis
    1.30
    Activations Density 0.474%

    No Known Activations