© 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. 20-GEMMASCOPE-RES-16K
    11. 196
    Prev
    Next
    INDEX
    Explanations

    HTML tags and their respective structures

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

    Text summaries

    np_acts-logits-general · gemini-2.0-flash

    narrative summaries

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    AddTagHelper
    -0.74
    AsUp
    -0.71
     Numerade
    -0.67
    ThroughAttribute
    -0.66
    ⓧ
    -0.63
    LookAnd
    -0.62
    oneofs
    -0.58
    WriteBarrier
    -0.57
    Espèce
    -0.57
    httphttps
    -0.56
    POSITIVE LOGITS
     summary
    1.73
    summary
    1.59
     Summary
    1.50
    Summary
    1.44
     SUMMARY
    1.40
     summaries
    1.32
    SUMMARY
    1.30
     sum
    1.29
    sum
    1.26
     summar
    1.24
    Activations Density 0.043%

    No Known Activations