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

    Neuronpedia

    Jacobian LensNEW
    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. 5685
    Prev
    Next
    INDEX
    Explanations

    specific place names and geographical features

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

    proper nouns and place names, particularly geographic locations and surnames.

    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
     współ
    -0.34
    PRESSED
    -0.27
     Dichtung
    -0.27
    EROS
    -0.26
     ת
    -0.24
    ECTO
    -0.24
    WEAR
    -0.23
     halbe
    -0.23
     sendok
    -0.23
    copy
    -0.22
    POSITIVE LOGITS
     Valley
    0.86
    StoryboardSegue
    0.78
     Creek
    0.78
     الحره
    0.76
     Farm
    0.75
     betweenstory
    0.73
     Hill
    0.73
     River
    0.72
     valley
    0.71
     Village
    0.71
    Activations Density 0.331%

    No Known Activations