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. MLP Out - 16k
    5. 0-GEMMASCOPE-MLP-16K
    6. 71
    Prev
    Next
    INDEX
    Explanations

    elements related to software APIs and structure definitions

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

    terms related to API client configurations and structures in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    참고
    -0.59
     himſelf
    -0.55
     neceff
    -0.50
    Packets
    -0.49
    Folders
    -0.49
     themſelves
    -0.49
    Playback
    -0.48
     saját
    -0.47
     itſelf
    -0.47
    They
    -0.46
    POSITIVE LOGITS
    MethodManager
    0.90
    MLLoader
    0.83
    ViewImports
    0.78
    ConstraintMaker
    0.76
    WebServlet
    0.75
    HtmlAttribute
    0.74
    ValueGeneration
    0.70
     AssemblyTitle
    0.70
     useParams
    0.69
    BeginContext
    0.68
    Activations Density 1.738%

    No Known Activations