© 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. 30-GEMMASCOPE-RES-16K
    11. 15676
    Prev
    Next
    INDEX
    Explanations

    references to recycling processes and activities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Units of volume or containers

    np_acts-logits-general · gemini-2.0-flash

    capacities and containers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     cucchia
    -0.40
    亿美元
    -0.37
    Pocket
    -0.36
     Pocket
    -0.36
     pocket
    -0.35
     mili
    -0.33
     bookmark
    -0.33
     cucchiaio
    -0.33
     puentes
    -0.32
    bullet
    -0.32
    POSITIVE LOGITS
     sacks
    0.75
     buckets
    0.72
     bags
    0.71
     suitcases
    0.71
     boxes
    0.71
     crates
    0.67
     tubs
    0.65
    bags
    0.64
     Boxes
    0.64
     crate
    0.63
    Activations Density 0.294%

    No Known Activations