© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 6511
    Prev
    Next
    INDEX
    Explanations

    geographic references related to the Middle East, specifically focusing on Iran and Syria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Muscat
    -0.47
    StructEnd
    -0.47
     Mauri
    -0.47
     oprot
    -0.46
    PMailer
    -0.46
    Alcal
    -0.46
     Mississauga
    -0.45
     Centa
    -0.45
     Aar
    -0.44
    issauga
    -0.43
    POSITIVE LOGITS
     Syria
    1.33
    Syria
    1.16
     Russia
    1.06
     Syrian
    1.02
    Russia
    1.01
     Iran
    0.97
     Russian
    0.94
     russia
    0.94
     Russians
    0.93
     Putin
    0.91
    Activations Density 0.355%

    No Known Activations