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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 7893
    Prev
    Next
    INDEX
    Explanations

    elements related to geographical and political contexts, particularly those concerning regions in Africa

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

    relating to places/regions

    np_acts-logits-general · gemini-2.0-flash

    southern places and regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     North
    -0.55
     NORTH
    -0.55
    North
    -0.55
     Northwestern
    -0.54
     Northern
    -0.53
    NORTH
    -0.52
    AsUp
    -0.51
     nord
    -0.51
     NW
    -0.51
     북
    -0.50
    POSITIVE LOGITS
     southeastern
    0.68
     SOUTHERN
    0.64
    SOUTH
    0.62
     southern
    0.61
    Southern
    0.59
     Southern
    0.59
    southern
    0.57
     southerly
    0.57
     SOUTH
    0.56
     Southland
    0.55
    Activations Density 0.554%

    No Known Activations