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 - 65k
    5. 4-GEMMASCOPE-MLP-65K
    6. 3
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols related to variables and constants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_4/width_65k/average_l0_66
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.4.hook_mlp_out
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Audiodateien
    -0.65
     newBuilder
    -0.61
    Referències
    -0.60
     StatelessWidget
    -0.56
    enumi
    -0.56
     المعيارى
    -0.55
    Manbalar
    -0.54
    
    -0.54
     isComment
    -0.52
    TagHelpers
    -0.50
    POSITIVE LOGITS
     AssemblyCulture
    0.58
    \}\\
    0.56
    ineno
    0.56
     vPvB
    0.56
    例文帳に追加
    0.52
    ortunadamente
    0.49
     chrétienne
    0.48
     positifs
    0.47
    wahati
    0.47
    niająca
    0.47
    Activations Density 0.566%

    No Known Activations