© 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. 14841
    Prev
    Next
    INDEX
    Explanations

    references to the word "Northern" in various contexts

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

    references to geographic locations, specifically the word "Northern" paired with place names.

    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
    southwest
    -0.51
    fören
    -0.39
     abandonné
    -0.37
    southeast
    -0.37
    estacks
    -0.36
    Rüyada
    -0.36
    DROP
    -0.36
     Piala
    -0.35
     поро
    -0.35
     étrangères
    -0.34
    POSITIVE LOGITS
    ChildScrollView
    0.61
    Бахар
    0.50
     Northern
    0.47
     الرياضيه
    0.47
    новништво
    0.46
    Northern
    0.46
    grà
    0.44
    blockList
    0.43
    wieś
    0.41
    WindowConstants
    0.41
    Activations Density 0.126%

    No Known Activations