© 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. 14-GEMMASCOPE-RES-16K
    11. 5151
    Prev
    Next
    INDEX
    Explanations

    references to old or outdated software and hardware

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    AndEndTag
    -0.50
    
    -0.31
    Newswire
    -0.30
     šir
    -0.28
    gså
    -0.28
     wachs
    -0.28
     által
    -0.28
    substack
    -0.28
    /*++
    -0.27
    応
    -0.27
    POSITIVE LOGITS
     old
    0.95
     antiquated
    0.89
     outdated
    0.88
     Old
    0.87
     vecchi
    0.87
     antigos
    0.85
    Old
    0.85
     retro
    0.84
     viejos
    0.84
     القديمة
    0.83
    Activations Density 0.334%

    No Known Activations