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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 6784
    Prev
    Next
    INDEX
    Explanations

    XML attributes and layout elements related to Android development

    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
     CYTHON
    -0.48
     pur
    -0.45
     sana
    -0.43
    دام
    -0.43
    thea
    -0.43
     Pur
    -0.43
    Archives
    -0.42
     StringVar
    -0.42
    tdata
    -0.42
    ปล
    -0.41
    POSITIVE LOGITS
     findViewById
    0.81
    findViewById
    0.71
    IBOutlet
    0.70
     snippetHide
    0.68
    RenderAtEndOf
    0.68
     يتيمه
    0.67
     IBOutlet
    0.66
     disambiguazione
    0.66
     getView
    0.65
     onCreateView
    0.64
    Activations Density 0.119%

    No Known Activations