© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 52703
    Prev
    Next
    INDEX
    Explanations

    various instances of the abbreviation "fa" associated with icons or visual indicators

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

    Font Awesome icons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    KommentareTeilen
    -0.79
    новниш
    -0.69
     snippetHide
    -0.66
    存于互联网档案馆
    -0.64
    setVerticalGroup
    -0.64
    ChildScrollView
    -0.63
    uxxxx
    -0.62
    tagHelperRunner
    -0.61
    InSection
    -0.60
    Искәрмәләр
    -0.59
    POSITIVE LOGITS
     fa
    1.01
    fortawesome
    0.96
     Fa
    0.89
     FontAwesome
    0.75
    Fa
    0.75
    fa
    0.70
     FA
    0.68
    FontAwesome
    0.65
    FA
    0.64
    FontAwesomeIcon
    0.63
    Activations Density 0.001%

    No Known Activations