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. 13-GEMMASCOPE-RES-16K
    6. 8329
    Prev
    Next
    INDEX
    Explanations

    the word "only" and its variations, indicating a focus on exclusivity or limitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    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
    -0.72
    $($
    -0.70
     condom
    -0.67
     hereof
    -0.63
     mellitus
    -0.63
     Calhoun
    -0.62
     Vex
    -0.62
     Tatiana
    -0.62
     Davenport
    -0.62
    Vex
    -0.61
    POSITIVE LOGITS
     only
    1.03
     Only
    0.92
     ONLY
    0.89
    ONLY
    0.86
    Sólo
    0.85
    Only
    0.81
    nly
    0.80
     Nur
    0.79
    Chỉ
    0.79
    僅
    0.76
    Activations Density 0.097%

    No Known Activations