Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 12719
    Prev
    Next
    INDEX
    Explanations

    references to the word "bud" and its variations in context related to plants or growth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Teh
    -0.71
    peration
    -0.67
    auru
    -0.65
    หาร
    -0.63
    esie
    -0.63
    MOP
    -0.63
     drow
    -0.62
    multirow
    -0.61
    OES
    -0.60
     Diab
    -0.60
    POSITIVE LOGITS
     Bud
    2.80
    Bud
    2.69
     bud
    2.56
     BUD
    2.54
    bud
    2.45
     buds
    2.26
    BUD
    2.23
     Buds
    2.13
    buds
    1.91
     Budd
    1.70
    Activations Density 0.109%

    No Known Activations