© 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. 5841
    Prev
    Next
    INDEX
    Explanations

    concepts related to projections in linear algebra or quantum mechanics

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

    concepts related to mathematical physics, particularly eigenvectors/eigenvalues, matrices, and quantum systems.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    technical and mathematical terminology related to eigenvalues, eigenvectors, and spectral decomposition in scientific contexts.

    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
    Autoritní
    -0.50
    ConstraintMaker
    -0.45
    Clement
    -0.44
     betweenstory
    -0.43
     gynhyrchwyd
    -0.42
    delwed
    -0.40
    ToTensor
    -0.40
    arran
    -0.40
    denly
    -0.39
    Commodity
    -0.39
    POSITIVE LOGITS
     eigenvalues
    1.11
     eigenvalue
    1.09
    eigen
    0.88
     eigen
    0.85
     Eigen
    0.84
    Eigen
    0.78
     eigenvectors
    0.72
    eig
    0.67
     eig
    0.66
     spectrum
    0.65
    Activations Density 1.191%

    No Known Activations