© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 13698
    Prev
    Next
    INDEX
    Explanations

    activities related to handling, transporting, and managing physical objects or materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Containers, bags, and packaging

    np_acts-logits-general · gemini-2.0-flash

    materials and containers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ComVisible
    -0.57
     tecla
    -0.56
     milligrams
    -0.52
    eara
    -0.51
     CommandType
    -0.50
    rstrip
    -0.49
     bolí
    -0.49
     atoms
    -0.48
    Hentet
    -0.48
     BorderSide
    -0.48
    POSITIVE LOGITS
     crates
    0.93
     buckets
    0.85
     pallets
    0.83
     tarp
    0.80
     plywood
    0.78
     crate
    0.78
     boxes
    0.78
     barrels
    0.76
     sacks
    0.75
     pallet
    0.73
    Activations Density 0.197%

    No Known Activations