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. 21-GEMMASCOPE-RES-16K
    6. 6921
    Prev
    Next
    INDEX
    Explanations

    code segments related to graphical user interface layout definitions in Android development

    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
    abestanden
    -0.86
    ########.
    -0.85
    UrlResolution
    -0.75
    WriteAttribute
    -0.74
     nahilalakip
    -0.73
     disambiguazione
    -0.71
    enderror
    -0.67
    Rhestr
    -0.67
     ujednoznacz
    -0.67
    SourceChecksum
    -0.67
    POSITIVE LOGITS
     layout
    0.80
     alignment
    0.73
     Layout
    0.71
    align
    0.67
    layout
    0.67
     vertical
    0.66
     horizontal
    0.66
    alignment
    0.65
    Layout
    0.63
    布局
    0.63
    Activations Density 0.410%

    No Known Activations