© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 10588
    Prev
    Next
    INDEX
    Explanations

    technical attributes and specifications of watches

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 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
     gehouden
    -0.59
     Trailer
    -0.54
     stork
    -0.53
    tirol
    -0.52
     AttributeSet
    -0.51
    exitRule
    -0.51
    kháu
    -0.50
     Pentecost
    -0.50
     rapides
    -0.50
     engraçadas
    -0.49
    POSITIVE LOGITS
     watch
    0.77
     watches
    0.76
     wrist
    0.74
    Jereo
    0.72
     wrists
    0.68
     Watches
    0.67
     rolex
    0.66
    lgari
    0.66
    watches
    0.66
     bezel
    0.66
    Activations Density 0.110%

    No Known Activations