© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3973
    Prev
    Next
    INDEX
    Explanations

    phrases related to the operation of truck loading and unloading processes

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

    forklift and warehouse operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Braid
    -0.59
     OFDb
    -0.56
     Krim
    -0.55
    Хьажоргаш
    -0.53
    QMetaType
    -0.52
    LookAnd
    -0.52
     Engra
    -0.52
    Precalculus
    -0.51
     Hütte
    -0.50
     encu
    -0.49
    POSITIVE LOGITS
     warehouse
    1.24
     warehousing
    1.09
     warehouses
    1.07
     Warehouse
    1.06
    Warehouse
    0.98
     inventory
    0.95
     pallet
    0.95
     forklift
    0.94
     Inventory
    0.94
     WARE
    0.91
    Activations Density 0.105%

    No Known Activations