© 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. 10488
    Prev
    Next
    INDEX
    Explanations

    log entries and logging actions

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

    Logging events (info, warn, error)

    np_acts-logits-general · gemini-2.0-flash

    info, warn, error logs

    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
    principalTable
    -0.68
    parsedMessage
    -0.66
    Rujuakan
    -0.65
    getOutputStream
    -0.61
     otomatig
    -0.60
     виправивши
    -0.58
     csal
    -0.56
    الحياه
    -0.56
    astéroïdes
    -0.56
     mijne
    -0.56
    POSITIVE LOGITS
    info
    0.68
     info
    0.68
     Info
    0.51
    iParam
    0.50
    INERY
    0.49
    Info
    0.49
    ])).
    0.48
     finer
    0.48
    WithIdentifier
    0.48
    routes
    0.47
    Activations Density 0.061%

    No Known Activations