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. 5-GEMMASCOPE-RES-16K
    6. 12718
    Prev
    Next
    INDEX
    Explanations

    references to winter and its related conditions

    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
    verwijspagina
    -1.02
    Jegyzetek
    -0.97
     calendriers
    -0.93
     تانيه
    -0.89
    eynman
    -0.88
     שוליים
    -0.87
    Παραπομπές
    -0.86
     étoient
    -0.85
     دیکھیے
    -0.84
     tagName
    -0.83
    POSITIVE LOGITS
     Winter
    1.65
     winter
    1.59
     Winters
    1.54
    Winter
    1.52
     WINTER
    1.47
    WINTER
    1.37
    winter
    1.35
     winters
    1.21
    冬
    1.14
     inverno
    0.99
    Activations Density 0.033%

    No Known Activations