© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1488
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Pickles" and its related terms

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

    references to data structures commonly used in programming, specifically dictionaries and pickles

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

    Pickles comic strip

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ities
    -0.62
    Linq
    -0.61
    сылкі
    -0.59
    mMap
    -0.59
    iyi
    -0.57
    Kara
    -0.57
    endgroup
    -0.57
    mainAxisSize
    -0.55
    uración
    -0.55
    dess
    -0.55
    POSITIVE LOGITS
     Pickle
    1.05
    Pickle
    1.01
     pickle
    0.95
     pickles
    0.95
     Pickles
    0.88
    pickle
    0.77
     ostavi
    0.74
     Vinegar
    0.72
     cucumbers
    0.72
     Gher
    0.71
    Activations Density 0.078%

    No Known Activations