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. 9059
    Prev
    Next
    INDEX
    Explanations

    references to frequency or quantity, particularly with the term "multiple."

    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
     voisins
    -0.69
     généraux
    -0.68
    łożyć
    -0.67
     placée
    -0.67
    Clik
    -0.67
     SAK
    -0.67
     verrez
    -0.66
     Grecs
    -0.65
     supérieurs
    -0.65
     conservé
    -0.65
    POSITIVE LOGITS
     multiple
    1.03
     myeloma
    0.97
    tiple
    0.93
    MULTIPLE
    0.92
     MULTIPLE
    0.91
    ihnachten
    0.91
     malen
    0.90
    hetamine
    0.87
     Multiple
    0.85
     multi
    0.85
    Activations Density 0.061%

    No Known Activations