© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 12966
    Prev
    Next
    INDEX
    Explanations

    references to geopolitical relationships and significant locations

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

    geographic locations and proper nouns, particularly cities and countries in international contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cestershire
    -0.30
    asyarakat
    -0.30
     Harz
    -0.29
    ⏟
    -0.28
     SUNY
    -0.26
     kadar
    -0.25
     Thü
    -0.24
    {%
    -0.24
     kommune
    -0.23
     Мол
    -0.23
    POSITIVE LOGITS
     London
    1.64
    London
    1.49
     Tokyo
    1.48
     Jakarta
    1.42
     Beijing
    1.41
     Bangkok
    1.39
     Londres
    1.39
     Madrid
    1.37
     Seoul
    1.35
     Berlin
    1.32
    Activations Density 0.528%

    No Known Activations