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. 11-GEMMASCOPE-RES-16K
    6. 5509
    Prev
    Next
    INDEX
    Explanations

    the word "particular" and its variations, indicating a focus on specificity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hands
    -0.86
     useEffect
    -0.82
     ItemStack
    -0.80
     BufferedImage
    -0.77
    dozer
    -0.77
     Doris
    -0.75
    
    -0.75
    slidesToShow
    -0.75
     Cuen
    -0.74
    RenderAtEndOf
    -0.73
    POSITIVE LOGITS
     particular
    0.80
     particulares
    0.76
    ticularly
    0.75
     partic
    0.71
     McGu
    0.69
    paddingVertical
    0.69
     McCarthy
    0.68
    particular
    0.68
     Particular
    0.67
    ity
    0.66
    Activations Density 0.061%

    No Known Activations