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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-GEMMASCOPE-RES-16K
    6. 2509
    Prev
    Next
    INDEX
    Explanations

    instances of the word "everyone" and its variations to identify inclusivity or collective sentiment across multiple contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IBOutlet
    -0.57
    ://
    -0.57
    zin
    -0.56
    kover
    -0.55
    _]
    -0.54
    先の
    -0.52
     Hil
    -0.52
    |<\
    -0.52
    aop
    -0.52
    笈
    -0.51
    POSITIVE LOGITS
     everyone
    2.00
    everyone
    1.94
     Everyone
    1.86
    Everyone
    1.85
     everybody
    1.81
    everybody
    1.77
     Everybody
    1.76
    Everybody
    1.68
     EVERYONE
    1.62
     iedereen
    1.25
    Activations Density 0.136%

    No Known Activations