© 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. 3516
    Prev
    Next
    INDEX
    Explanations

    academic references and citations contained within the text

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

    "(Eds.)" or "Ed."

    np_acts-logits-general · gemini-2.0-flash

    (Eds.) followed by book titles

    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
    featureID
    -0.65
     
    -0.59
    клопе
    -0.59
    unque
    -0.58
     TAMBÉM
    -0.58
     ligiloj
    -0.57
    UniformLocation
    -0.55
    UMBIA
    -0.55
     löyty
    -0.55
    _));
    -0.54
    POSITIVE LOGITS
     ed
    0.89
     eds
    0.79
    Ed
    0.78
     editor
    0.77
    ed
    0.73
    eds
    0.73
     Ed
    0.72
    Eds
    0.71
     Eds
    0.70
     editors
    0.66
    Activations Density 0.071%

    No Known Activations