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. 12-GEMMASCOPE-RES-16K
    6. 15382
    Prev
    Next
    INDEX
    Explanations

    descriptions of coatings and finishes on materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.79
    IonicModule
    -0.69
     للمعارف
    -0.64
    مقاله
    -0.62
     jScrollPane
    -0.61
    HStack
    -0.57
    FetchType
    -0.57
    izational
    -0.57
     CreateTagHelper
    -0.56
     chặt
    -0.55
    POSITIVE LOGITS
    coat
    0.69
     coating
    0.68
     coatings
    0.66
     coat
    0.61
    arnish
    0.59
     luster
    0.59
     gloss
    0.59
     coats
    0.57
     povr
    0.56
     buffed
    0.55
    Activations Density 0.289%

    No Known Activations