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. 8676
    Prev
    Next
    INDEX
    Explanations

    references to fruits and their characteristics

    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
     Alvar
    -0.66
     Saks
    -0.63
     fathoms
    -0.63
     bezeichneter
    -0.62
     Borno
    -0.61
     Burrow
    -0.61
     Brahman
    -0.61
     heels
    -0.60
     sää
    -0.60
     Holocene
    -0.58
    POSITIVE LOGITS
     fruit
    1.70
     fruits
    1.69
     FRUIT
    1.55
     Fruit
    1.55
     Fruits
    1.53
    fruit
    1.48
    fruits
    1.47
    Fruit
    1.47
    Fruits
    1.45
     fruta
    1.29
    Activations Density 0.230%

    No Known Activations