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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 29208
    Prev
    Next
    INDEX
    Explanations

    floral arrangements and offerings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    AddTagHelper
    -0.89
    :✨
    -0.87
     gyhoeddwyd
    -0.79
    SpringBootTest
    -0.78
     disambiguazione
    -0.72
     @"/
    -0.69
     imagui
    -0.68
    <unused15>
    -0.65
    <unused14>
    -0.65
    <pad>
    -0.65
    POSITIVE LOGITS
     flowers
    0.56
     bloemen
    0.53
     bouquets
    0.49
     florales
    0.42
     Flowers
    0.41
    Flowers
    0.41
     bouquet
    0.40
     roses
    0.37
     çiçek
    0.36
     FLOWERS
    0.35
    Activations Density 0.007%

    No Known Activations