© 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 EvalsExportsinterp-engineNEWAPI 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. 7175
    Prev
    Next
    INDEX
    Explanations

    references to historical or political conflicts involving Middle Eastern countries

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

    Middle Eastern places and concepts

    np_acts-logits-general · gemini-2.0-flash

    Middle East geography

    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
     brasili
    -0.47
     Glacier
    -0.42
    Skocz
    -0.41
     Odin
    -0.41
     Glor
    -0.39
     Odisha
    -0.39
     Leif
    -0.38
    Nebraska
    -0.37
     Bem
    -0.37
    Alaska
    -0.37
    POSITIVE LOGITS
     Syria
    1.27
     Syrian
    1.25
    Syria
    1.07
     Arab
    1.06
     Jordanian
    1.00
     Damascus
    1.00
     Syrians
    0.95
     Lebanon
    0.94
     Arabic
    0.94
     Lebanese
    0.94
    Activations Density 0.346%

    No Known Activations