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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11118
    Prev
    Next
    INDEX
    Explanations

    references to sources and citations in the text

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

    Text after URLs or publications

    np_acts-logits-general · gemini-2.0-flash

    sources, URLs, and publications

    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
    PLEMENT
    -0.54
     newspaper
    -0.52
    таратура
    -0.51
    jelent
    -0.47
    lepaskan
    -0.46
     book
    -0.45
     Tribune
    -0.45
     Mercantile
    -0.44
    IRIS
    -0.44
     répé
    -0.44
    POSITIVE LOGITS
    RenderAtEndOf
    1.05
    expandindo
    0.95
    featureID
    0.80
    脚注の使い方
    0.76
    protoimpl
    0.75
    webElementXpaths
    0.70
    تقاوى
    0.70
    complexContent
    0.69
     @"/
    0.69
    WriteBarrier
    0.69
    Activations Density 0.130%

    No Known Activations