© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14733
    Prev
    Next
    INDEX
    Explanations

    patterns in structured data, particularly related to JSON objects and their fields

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

    Strings containing several digits and/or characters

    np_acts-logits-general · gemini-2.0-flash

    alphanumeric sequences

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     EconPapers
    -0.81
    httphttps
    -0.73
     للاسماء
    -0.72
     lenker
    -0.68
    
    -0.68
     typelib
    -0.66
    MLLoader
    -0.66
    رشف
    -0.66
     Geiſt
    -0.64
    ſchaft
    -0.64
    POSITIVE LOGITS
     etc
    0.57
    abc
    0.52
     abc
    0.52
     ABC
    0.52
    abcdef
    0.49
    ABC
    0.49
    abcdefghijklmnop
    0.47
    abcd
    0.46
    etc
    0.43
     XYZ
    0.42
    Activations Density 0.468%

    No Known Activations