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. 11046
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "you" and its variations in contextually relevant sentences

    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
     RoutedEventArgs
    -1.10
    adaptiveStyles
    -0.91
     SafeMath
    -0.77
     nahilalakip
    -0.73
     Réponses
    -0.72
    MessageTagHelper
    -0.72
     NSCoder
    -0.69
    Билгалдахарш
    -0.69
     initWithFrame
    -0.67
    subpackage
    -0.67
    POSITIVE LOGITS
     else
    0.90
     alternatively
    0.85
     otherwise
    0.74
     or
    0.71
     oder
    0.69
     any
    0.66
    それとも
    0.65
    else
    0.63
    otherwise
    0.62
     conversely
    0.62
    Activations Density 0.244%

    No Known Activations