© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6709
    Prev
    Next
    INDEX
    Explanations

    patterns in regular expressions, particularly the caret symbol used to denote the start of a string

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mathrm
    -0.59
    المل
    -0.57
     שוליים
    -0.57
    lahoma
    -0.56
    MathML
    -0.56
    piece
    -0.56
    çı
    -0.55
     Salz
    -0.55
     Duda
    -0.55
     daz
    -0.55
    POSITIVE LOGITS
     ^
    2.57
     "^
    1.89
    .^
    1.85
     '^
    1.81
    '^
    1.75
    ("^
    1.73
    ^^^
    1.69
    -^
    1.66
    "^
    1.58
     ^^
    1.58
    Activations Density 0.188%

    No Known Activations