© 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. 0-GEMMASCOPE-RES-16K
    11. 3799
    Prev
    Next
    INDEX
    Explanations

    instances of the word "remaining."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    migrationBuilder
    -0.65
    MessageTagHelper
    -0.62
    ésultats
    -0.60
    出版年
    -0.60
     verſch
    -0.59
    Попис
    -0.59
     autorytatywna
    -0.58
    
    -0.58
    Hozzáférés
    -0.58
     giebt
    -0.57
    POSITIVE LOGITS
    Remaining
    0.67
     Remaining
    0.66
     remaining
    0.65
    remaining
    0.58
     Nigeria
    0.56
     remainder
    0.55
     remain
    0.52
     Singer
    0.49
    remain
    0.49
    Software
    0.49
    Activations Density 0.157%

    No Known Activations