© 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. 11-GEMMASCOPE-RES-16K
    11. 9542
    Prev
    Next
    INDEX
    Explanations

    elements related to formality and etiquette in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Varint
    -0.47
     насељу
    -0.47
     Patch
    -0.45
     base
    -0.45
    theil
    -0.44
    omitempty
    -0.44
     defoli
    -0.44
    base
    -0.44
     continúas
    -0.43
     زد
    -0.43
    POSITIVE LOGITS
     dignified
    0.77
     formality
    0.76
     stately
    0.76
     formales
    0.74
     solemn
    0.73
     formal
    0.72
    Formal
    0.71
     Formal
    0.71
    المناصب
    0.70
     formalities
    0.69
    Activations Density 0.522%

    No Known Activations