© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 97397
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "chunks" or "chunking" in data handling or narrative contexts

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

    chuck, chunk, or chuckle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    didSet
    -0.49
     للمعارف
    -0.48
    hasErrors
    -0.47
    }{*}{
    -0.47
    ⓘ
    -0.44
     LoggerFactory
    -0.43
     erwartet
    -0.40
    mybatisplus
    -0.38
    حياتها
    -0.37
    >";
    -0.36
    POSITIVE LOGITS
    chunk
    1.39
     chunk
    1.38
    Chunk
    1.37
     Chunk
    1.34
     chunks
    1.15
    CHUNK
    1.12
    chunks
    1.08
    Chunks
    1.03
    Chuck
    0.85
     Chuck
    0.83
    Activations Density 0.003%

    No Known Activations