© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 41089
    Prev
    Next
    INDEX
    Explanations

    references to bags and their various types or contexts

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

    bag or bags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Not in Any Lists

    No Comments

    Negative Logits
     Urbana
    -0.52
     Champaign
    -0.50
    neri
    -0.48
     Hardin
    -0.48
    timi
    -0.47
     verhe
    -0.47
     cerah
    -0.47
    '])
    -0.47
     Illinois
    -0.47
     propTypes
    -0.47
    POSITIVE LOGITS
     bag
    1.33
    Bag
    1.28
     Bag
    1.25
     BAG
    1.23
    bag
    1.14
     Bags
    1.11
    Bags
    1.10
     bags
    1.09
    BAG
    1.03
    bags
    0.94
    Activations Density 0.006%

    No Known Activations