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. 1-GEMMASCOPE-MLP-16K
    6. 8743
    Prev
    Next
    INDEX
    Explanations

    terms related to cosmetic enhancement and beauty products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_mlp_out
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.81
     تضيفلها
    -0.76
     Waray
    -0.63
     nakalista
    -0.60
    contentLoaded
    -0.58
     ErrInvalid
    -0.57
    BeginContext
    -0.55
    يميديا
    -0.54
    ContextHolder
    -0.54
    RegistryLite
    -0.53
    POSITIVE LOGITS
    rouvez
    0.56
     khẩu
    0.54
    BOOT
    0.53
    ització
    0.53
    kező
    0.52
    cesi
    0.51
    megen
    0.50
     shadow
    0.49
     envelo
    0.49
     shadows
    0.48
    Activations Density 0.197%

    No Known Activations