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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 2789
    Prev
    Next
    INDEX
    Explanations

    information related to educational backgrounds and accomplishments in the arts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.73
     AssemblyCompany
    -0.57
     Baillargeon
    -0.51
     ModelExpression
    -0.47
    WebElementEntity
    -0.46
    ידות
    -0.45
    twimg
    -0.45
    UnsafeEnabled
    -0.44
     disambiguazione
    -0.44
    DOI
    -0.44
    POSITIVE LOGITS
     arts
    1.02
     Arts
    0.88
    arts
    0.80
    Arts
    0.79
     ARTS
    0.78
    ARTS
    0.75
     Artist
    0.74
     artistic
    0.74
     Creative
    0.72
     artists
    0.71
    Activations Density 0.187%

    No Known Activations