© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 5734
    Prev
    Next
    INDEX
    Explanations

    parentheses and their significance in written content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reſ
    -2.36
     Theſe
    -2.35
     Anſ
    -2.34
     ―――――
    -2.26
     Houſe
    -2.25
     Monfieur
    -2.21
     Diſ
    -2.20
     iſt
    -2.16
     Eſ
    -2.15
     ſche
    -2.15
    POSITIVE LOGITS
     (
    2.33
     [
    1.38
     "
    1.31
     
    1.31
     “
    1.29
    ↵↵
    1.27
    ↵
    1.25
     I
    1.23
      
    1.13
     '
    1.12
    Activations Density 0.707%

    No Known Activations