© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 9199
    Prev
    Next
    INDEX
    Explanations

    the word "respectively" and its occurrences in relation to comparisons or listings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.36
     anti
    -0.35
     shared
    -0.34
     premise
    -0.33
     portata
    -0.33
     ибо
    -0.33
    guien
    -0.32
     liderança
    -0.32
     manquante
    -0.32
     guidance
    -0.31
    POSITIVE LOGITS
     disambiguazione
    0.84
    Core
    0.83
     Core
    0.76
     Versions
    0.74
     versions
    0.73
     respectively
    0.68
     Taktlose
    0.66
    出版年
    0.65
    IntoConstraints
    0.65
     queſta
    0.61
    Activations Density 0.122%

    No Known Activations