© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 9490
    Prev
    Next
    INDEX
    Explanations

    references to mathematical concepts, especially related to bounds and estimates

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Gegenwart
    -0.34
    tagHelperRunner
    -0.33
    enfance
    -0.32
     során
    -0.32
     secondaire
    -0.31
     secondaires
    -0.30
     elettrico
    -0.30
     majorité
    -0.29
     krę
    -0.28
     buurt
    -0.28
    POSITIVE LOGITS
    EndContext
    0.79
     protoimpl
    0.74
    
    0.72
    kháu
    0.71
    artament
    0.67
    featureID
    0.66
     Autorizaciones
    0.66
    səhifə
    0.65
    FontOfSize
    0.65
    Jeografia
    0.64
    Activations Density 1.953%

    No Known Activations