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. 22-GEMMASCOPE-RES-16K
    6. 13984
    Prev
    Next
    INDEX
    Explanations

    phrases related to holiday celebrations and their preparations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iprot
    -0.48
    amazonaws
    -0.48
     dettaglio
    -0.46
    omitempty
    -0.45
    nought
    -0.43
    enosti
    -0.43
     sostu
    -0.43
    ээ
    -0.42
     gång
    -0.41
     nube
    -0.41
    POSITIVE LOGITS
     Christmas
    2.33
     Thanksgiving
    2.05
     holidays
    2.04
     christmas
    2.01
     holiday
    2.00
    Christmas
    1.98
     Halloween
    1.95
     CHRISTMAS
    1.93
     Xmas
    1.89
     Easter
    1.87
    Activations Density 0.463%

    No Known Activations