© 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. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 110903
    Prev
    Next
    INDEX
    Explanations

    references to fiber optics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fiber
    -2.30
     fibre
    -2.25
     Fiber
    -2.14
    fiber
    -2.08
    Fiber
    -2.06
     Fibre
    -1.97
     fibers
    -1.88
    Fibre
    -1.86
     fibres
    -1.86
     fibra
    -1.74
    POSITIVE LOGITS
    Missing
    0.33
     ex
    0.33
    lago
    0.31
    semantics
    0.30
     encontramos
    0.30
     lesiones
    0.30
     parall
    0.30
    tvguidetime
    0.30
     dapur
    0.29
    auto
    0.29
    Activations Density 0.003%

    No Known Activations