© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15787
    Prev
    Next
    INDEX
    Explanations

    references to Australia and its culture or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.59
    ValueStyle
    -0.49
    #
    -0.40
     Dungeons
    -0.39
    _{[
    -0.39
    newBuilder
    -0.39
    ListItemIcon
    -0.38
     przewod
    -0.38
     createState
    -0.37
     setPrice
    -0.37
    POSITIVE LOGITS
     Australian
    2.17
     Australia
    2.09
    Australian
    2.06
    Australia
    2.03
     Australians
    1.91
     AUSTRALIA
    1.87
     Aussie
    1.87
     Australien
    1.84
     Austr
    1.80
     australian
    1.77
    Activations Density 0.173%

    No Known Activations