© 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. 210
    Prev
    Next
    INDEX
    Explanations

    variables and parameters related to time and date in programming contexts

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

    Equals signs, colons, and variable assignments

    np_acts-logits-general · gemini-2.0-flash

    swift assignments and code structure

    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
    باره
    -0.52
    ыгана
    -0.52
     erstat
    -0.50
    BarStyle
    -0.48
    ximation
    -0.47
     Meld
    -0.47
     سكانية
    -0.47
     onAnimation
    -0.46
     ingenting
    -0.46
     للمعارف
    -0.45
    POSITIVE LOGITS
    try
    0.61
     "\(
    0.61
     try
    0.60
    richTextPanel
    0.58
     présente
    0.55
    !("{}",
    0.55
     ujednoznacz
    0.54
     виправивши
    0.54
    Defaults
    0.54
    WindowConstants
    0.54
    Activations Density 0.158%

    No Known Activations