© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 7008
    Prev
    Next
    INDEX
    Explanations

    complex mathematical or programming structures and syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ing
    -0.94
     ***!
    -0.92
    ations
    -0.90
     Gump
    -0.80
    INS
    -0.78
    ありません
    -0.78
    es
    -0.77
    voorbeeld
    -0.75
    ins
    -0.72
    mps
    -0.69
    POSITIVE LOGITS
    ядок
    0.94
     חיצוניים
    0.86
    engeti
    0.83
     Steen
    0.81
     Dooley
    0.78
    ตร์
    0.77
     quæ
    0.77
    Hul
    0.76
     Webber
    0.76
    سانی
    0.75
    Activations Density 0.335%

    No Known Activations