© 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. 24-GEMMASCOPE-RES-16K
    11. 9423
    Prev
    Next
    INDEX
    Explanations

    references to Australian authors and literature

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

    Australia, Australian, Australians

    np_acts-logits-general · gemini-2.0-flash

    Australia and Australians

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
     flavorful
    -0.55
     mußten
    -0.54
     daß
    -0.54
    FAVOR
    -0.52
     uș
    -0.51
     favors
    -0.49
     ๆ
    -0.49
     flavor
    -0.49
     ее
    -0.48
     enfans
    -0.48
    POSITIVE LOGITS
     Australian
    1.39
     Australia
    1.34
    Australian
    1.27
     Australians
    1.24
    Australia
    1.22
     Melbourne
    1.21
     Queensland
    1.20
     Aussie
    1.19
     Brisbane
    1.16
     AUSTRALIA
    1.16
    Activations Density 0.482%

    No Known Activations