© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 13524
    Prev
    Next
    INDEX
    Explanations

    conjunctions and connectors that emphasize a narrative or build upon ideas

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     herself
    -0.75
    etc
    -0.74
    خرى
    -0.67
     etc
    -0.67
     Itself
    -0.66
     THEM
    -0.65
     Himself
    -0.65
     Etc
    -0.65
     himself
    -0.64
    herself
    -0.64
    POSITIVE LOGITS
     although
    1.62
     while
    1.40
    although
    1.27
     meskipun
    1.25
     aunque
    1.19
     when
    1.19
     despite
    1.17
     it
    1.16
     meski
    1.14
     though
    1.13
    Activations Density 0.450%

    No Known Activations