© 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. 3752
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific deity, particularly in a devotional context

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

    "Nar" or "Narasimha"

    np_acts-logits-general · gemini-2.0-flash

    Narasimha

    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
     AssemblyProduct
    -0.64
    AntiForgeryToken
    -0.57
     surla
    -0.56
    titleMargin
    -0.55
     LoggerFactory
    -0.52
    entuh
    -0.50
    האם
    -0.50
    afficheront
    -0.50
     بيها
    -0.49
    TagHelper
    -0.49
    POSITIVE LOGITS
    principalTable
    0.73
     Nar
    0.70
    Nar
    0.68
     nar
    0.57
     насеље
    0.53
    Personensuche
    0.51
     Narayan
    0.47
     acondicionado
    0.46
    Notas
    0.44
     aidant
    0.44
    Activations Density 0.162%

    No Known Activations