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. 5-GEMMASCOPE-RES-16K
    6. 4446
    Prev
    Next
    INDEX
    Explanations

    the emphasis on the word "so" and its varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    μία
    -0.76
    indépendance
    -0.75
     vertes
    -0.73
     Breton
    -0.71
     Winfrey
    -0.71
     hond
    -0.70
    Portail
    -0.70
     wur
    -0.70
     Catania
    -0.70
     Brugge
    -0.69
    POSITIVE LOGITS
     so
    1.71
     So
    1.53
    So
    1.46
     SO
    1.39
    so
    1.32
    Sooo
    1.19
     Så
    1.12
    SO
    1.08
     sooo
    1.04
     sooooo
    1.03
    Activations Density 0.101%

    No Known Activations