© 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. 4064
    Prev
    Next
    INDEX
    Explanations

    mentions of titles or honorifics, particularly "Sir" or related variations

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

    starting with "Kir", "Sir", "Cir", "Fir", or "Vir"

    np_acts-logits-general · gemini-2.0-flash

    Sira, Kirmayer, Firth, Circuit, Kirby, Miranda

    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
     esternos
    -0.69
    EndGlobalSection
    -0.62
    KURZBESCHREIBUNG
    -0.62
     Either
    -0.60
    ItemBackground
    -0.60
    PDOException
    -0.59
     Dä
    -0.57
    Either
    -0.57
    Derbyniad
    -0.56
     either
    -0.56
    POSITIVE LOGITS
     Sira
    0.65
    irkus
    0.58
    vir
    0.58
    Fir
    0.58
    Kir
    0.58
    Vir
    0.55
     Kir
    0.54
     rails
    0.54
     Pir
    0.54
     BIR
    0.54
    Activations Density 0.121%

    No Known Activations