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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4280
    Prev
    Next
    INDEX
    Explanations

    media types and their associated properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumii
    -0.67
     дописавши
    -0.57
    AutoField
    -0.56
     Sunday
    -0.53
    ParallelGroup
    -0.53
     Satur
    -0.53
    UnusedPrivate
    -0.52
    ViewImports
    -0.52
    GraphicsUnit
    -0.51
     onPostExecute
    -0.50
    POSITIVE LOGITS
    verwijspagina
    0.61
     oprot
    0.57
    avadoc
    0.56
    resentation
    0.55
    ostok
    0.54
    executor
    0.51
    iettivo
    0.51
    ẢN
    0.49
    omiya
    0.49
     División
    0.48
    Activations Density 0.114%

    No Known Activations