© 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. 36-GEMMASCOPE-RES-16K
    11. 13213
    Prev
    Next
    INDEX
    Explanations

    references to specific countries and their political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.55
     protoimpl
    -0.55
    MLLoader
    -0.50
    BufferException
    -0.48
    ConverterFactory
    -0.47
    SharedDtor
    -0.47
     UIApplication
    -0.45
    JNIEnv
    -0.43
    ANTLR
    -0.43
    पया
    -0.42
    POSITIVE LOGITS
     Qatar
    0.95
    Qatar
    0.81
    Doha
    0.73
    🇶
    0.73
     Doha
    0.71
     qatar
    0.70
     قطر
    0.68
     Hama
    0.55
    Hama
    0.54
     Bahrain
    0.49
    Activations Density 0.186%

    No Known Activations