© 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. 7788
    Prev
    Next
    INDEX
    Explanations

    references to historical events related to military campaigns and territorial changes

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

    geographical locations and place names, particularly cities and regions in Central Asia and the Middle East.

    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
     Majefty
    -0.87
    ſelf
    -0.83
     myſelf
    -0.79
    <unused43>
    -0.77
    <unused47>
    -0.77
    <unused51>
    -0.76
    <unused52>
    -0.76
    <unused23>
    -0.76
    <unused8>
    -0.76
    <unused16>
    -0.76
    POSITIVE LOGITS
     zám
    0.36
    現在の
    0.35
    attuale
    0.33
     hoje
    0.32
     heutige
    0.31
    aujourd
    0.30
     hvilken
    0.29
     correos
    0.29
     modern
    0.28
     nyky
    0.28
    Activations Density 0.452%

    No Known Activations