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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 2181
    Prev
    Next
    INDEX
    Explanations

    references to cultural celebrations and seasonal festivals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nonatomic
    -0.71
     nonatomic
    -0.51
     INC
    -0.49
     $
    -0.49
     uintptr
    -0.47
     op
    -0.46
     surla
    -0.46
     che
    -0.45
    Przypisy
    -0.45
    ْم
    -0.44
    POSITIVE LOGITS
     Christmas
    1.38
    Christmas
    1.38
     CHRISTMAS
    1.38
     christmas
    1.32
     navideña
    1.32
     Xmas
    1.31
     xmas
    1.30
     Easter
    1.30
    christmas
    1.28
    Easter
    1.28
    Activations Density 0.127%

    No Known Activations