© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10884
    Prev
    Next
    INDEX
    Explanations

    references to historical political figures and their roles

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

    before titles (king, emperor, tsar)

    np_acts-logits-general · gemini-2.0-flash

    royal succession

    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
    WaitGroup
    -0.63
    XmlAccessType
    -0.61
     الرياضيه
    -0.56
    OrBuilder
    -0.50
     Pfarrer
    -0.48
    انيف
    -0.47
    insee
    -0.46
    wpi
    -0.45
    lée
    -0.45
     technician
    -0.45
    POSITIVE LOGITS
     king
    1.51
     King
    1.44
     kings
    1.43
     royal
    1.41
     monarch
    1.37
     throne
    1.35
     monarchs
    1.32
     royalty
    1.27
     monarchy
    1.25
     royals
    1.24
    Activations Density 0.609%

    No Known Activations