© 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. 11119
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations or entities related to Khurasan

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

    "Kh" followed by certain letters

    np_acts-logits-general · gemini-2.0-flash

    Khurasan

    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
    WriteAttribute
    -0.84
    rungsseite
    -0.82
    AutoScaleMode
    -0.81
     referenties
    -0.78
     againſt
    -0.75
     Efq
    -0.75
    NameInMap
    -0.74
    afficheront
    -0.70
    ništvo
    -0.69
     Stare
    -0.69
    POSITIVE LOGITS
     Kh
    0.57
     Kha
    0.51
     kh
    0.50
     ra
    0.43
    tiary
    0.42
     Bla
    0.42
     micro
    0.41
    Legit
    0.41
    endurch
    0.40
     cut
    0.40
    Activations Density 0.090%

    No Known Activations