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

    Neuronpedia

    Jacobian LensNEW
    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. 24-GEMMASCOPE-RES-16K
    11. 10324
    Prev
    Next
    INDEX
    Explanations

    references to a specific subject or individual named "Sar."

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

    Text containing the substring "Sar"

    np_acts-logits-general · gemini-2.0-flash

    Sar- followed by common completions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    [](
    -0.55
    NewLabel
    -0.52
    atimes
    -0.50
     etab
    -0.49
     surface
    -0.48
    Życiorys
    -0.47
    kies
    -0.47
     monde
    -0.47
     EconPapers
    -0.46
     MonoBehaviour
    -0.46
    POSITIVE LOGITS
    Sar
    0.58
    WriteHeader
    0.58
     ModelExpression
    0.58
     onOptions
    0.57
     raiſ
    0.57
     للاسماء
    0.56
     mijne
    0.53
    fillType
    0.53
     sar
    0.53
    dirond
    0.52
    Activations Density 0.207%

    No Known Activations