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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4974
    Prev
    Next
    INDEX
    Explanations

    the word "stream" in a computing context

    oai_token-act-pair · gemini-2.0-flash

    stream

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stream
    -2.97
    stream
    -2.91
    Stream
    -2.81
     Stream
    -2.80
     streams
    -2.41
     STREAM
    -2.28
    streams
    -2.19
     Streams
    -2.17
    STREAM
    -2.14
    Streams
    -1.96
    POSITIVE LOGITS
    MemoryWarning
    0.67
     OkHttpClient
    0.62
    InjectAttribute
    0.62
     makeStyles
    0.60
     BitmapFactory
    0.59
     EconPapers
    0.59
    matchCondition
    0.57
    WEBPACK
    0.56
    aarrggbb
    0.56
     Shakspeare
    0.56
    Activations Density 0.339%

    No Known Activations