Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12662
    Prev
    Next
    INDEX
    Explanations

    instances of the word "though" or "although" as transitional phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Spoljašnje
    -0.63
    出版年
    -0.62
     Efq
    -0.62
    DockStyle
    -0.61
     GNA
    -0.60
    ufact
    -0.60
    enumi
    -0.59
    ittarius
    -0.57
    issory
    -0.56
    بوابة
    -0.56
    POSITIVE LOGITS
     toutefois
    0.94
     Правда
    0.87
    прочем
    0.83
    however
    0.80
    though
    0.78
     however
    0.78
     freilich
    0.77
     though
    0.76
     admittedly
    0.75
     perhaps
    0.74
    Activations Density 0.142%

    No Known Activations