© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101508
    Prev
    Next
    INDEX
    Explanations

    references to diagonal structures or elements in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Universitario
    -0.56
     Inscrivez
    -0.50
     éste
    -0.47
    initWithFrame
    -0.47
     marinho
    -0.46
     mł
    -0.46
     betreft
    -0.46
     miejsco
    -0.45
     Suivez
    -0.45
     lecz
    -0.44
    POSITIVE LOGITS
     Diagonal
    1.07
     diagonal
    1.03
    Diagonal
    0.96
    diagonal
    0.94
     diagonally
    0.80
     diagon
    0.76
    ogonal
    0.71
     transversal
    0.63
     Diag
    0.63
     diag
    0.63
    Activations Density 0.010%

    No Known Activations