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. 16-GEMMASCOPE-RES-16K
    6. 12327
    Prev
    Next
    INDEX
    Explanations

    the definite article "the" and its variations in terms of context or usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "the" (often capitalized)

    np_acts-logits-general · gemini-2.0-flash

    the followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BitmapFactory
    -0.65
     Efq
    -0.64
    IonicModule
    -0.62
     requestCode
    -0.60
     actionBar
    -0.60
    PMailer
    -0.59
     sirva
    -0.57
    RefreshLayout
    -0.56
    parsedMessage
    -0.55
     contextLoads
    -0.55
    POSITIVE LOGITS
     corresponding
    0.62
     corrispond
    0.61
    laston
    0.60
    addContainerGap
    0.59
    pædia
    0.59
     مفص
    0.57
     препратки
    0.57
    archiviato
    0.54
    corresponding
    0.54
    处的
    0.53
    Activations Density 0.483%

    No Known Activations