© 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 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. 1712
    Prev
    Next
    INDEX
    Explanations

    patterns involving special characters, particularly those used in regular expressions

    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
     Monark
    -0.47
     determinate
    -0.45
     angeb
    -0.45
     fuo
    -0.43
     bowiem
    -0.42
     Fils
    -0.41
    Anar
    -0.40
    HasOne
    -0.40
     adev
    -0.40
    Double
    -0.40
    POSITIVE LOGITS
     تضيفلها
    0.96
    Personendaten
    0.95
    ChildScrollView
    0.79
     nahilalakip
    0.72
    الدراسه
    0.71
     intptr
    0.71
    argout
    0.70
    достатки
    0.69
    twimg
    0.69
    disposing
    0.69
    Activations Density 0.488%

    No Known Activations