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. 15362
    Prev
    Next
    INDEX
    Explanations

    the presence of special formatting tokens or opening phases that indicate the start of significant content

    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
     المعيارى
    -0.69
    WaitGroup
    -0.68
    BeginContext
    -0.66
     AsyncTask
    -0.63
    setVerticalGroup
    -0.61
     RSSSF
    -0.61
     المعرف
    -0.60
     spectateurs
    -0.59
    KEYCODE
    -0.59
     bière
    -0.57
    POSITIVE LOGITS
     designer
    1.01
     fashion
    0.99
     designers
    0.89
     stylist
    0.83
     inspiration
    0.80
     boutiques
    0.78
     creative
    0.78
     Fashion
    0.78
    fashion
    0.77
     couture
    0.74
    Activations Density 0.147%

    No Known Activations