© 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. 18-GEMMASCOPE-RES-16K
    11. 8377
    Prev
    Next
    INDEX
    Explanations

    patterns and structures related to regular expressions and their components

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

    Regular expressions and patterns

    np_acts-logits-general · gemini-2.0-flash

    regex capture groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Main
    -0.57
     main
    -0.53
    Main
    -0.51
     Distribu
    -0.49
    main
    -0.47
     mains
    -0.47
     rue
    -0.47
    respec
    -0.43
    Affection
    -0.43
     Twin
    -0.43
    POSITIVE LOGITS
     الحره
    0.76
    \{\\
    0.70
     InputDecoration
    0.65
    出版年
    0.64
    μως
    0.60
    ########.
    0.60
     dAtA
    0.60
    *(
    0.60
     seba
    0.60
     BorderRadius
    0.59
    Activations Density 0.296%

    No Known Activations