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. 18-GEMMASCOPE-MLP-65K
    6. 111
    Prev
    Next
    INDEX
    Explanations

    references to online dating services and promotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_18/width_65k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.18.hook_mlp_out
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.69
    coroutines
    -0.67
     surla
    -0.66
    tvguidetime
    -0.65
     autorytatywna
    -0.65
    المناصب
    -0.63
    bufio
    -0.62
    #+#
    -0.61
    HandlerContext
    -0.60
    ContentAsync
    -0.60
    POSITIVE LOGITS
     websites
    0.88
     Websites
    0.70
     website
    0.68
     sites
    0.67
    网站
    0.62
     online
    0.62
    Websites
    0.61
    Online
    0.60
     Online
    0.60
    online
    0.60
    Activations Density 0.165%

    No Known Activations