© 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. 20-GEMMASCOPE-RES-16K
    11. 3032
    Prev
    Next
    INDEX
    Explanations

    symbols and mathematical notation relevant to tensor algebra and matrix operations

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

    mathematical symbols and notation, particularly Greek letters and mathematical variables.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    This neuron activates on mathematical symbols and variables in mathematical equations, particularly focusing on capital letters that represent mathematical objects or functions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsMutable
    -0.76
     kasarigan
    -0.76
     يتيمه
    -0.74
    PerformLayout
    -0.68
     Италијани
    -0.66
    Хьажоргаш
    -0.63
     CreateTagHelper
    -0.61
    mpagne
    -0.61
     Wikimedijinoj
    -0.61
     Geor
    -0.60
    POSITIVE LOGITS
     séjours
    0.42
     fundido
    0.39
    zarchiwizowane
    0.37
     paille
    0.36
     psicológico
    0.35
     adjunto
    0.35
    holdet
    0.35
     ouvriers
    0.35
     løpet
    0.35
     perlas
    0.34
    Activations Density 1.699%

    No Known Activations