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. 8910
    Prev
    Next
    INDEX
    Explanations

    the concept of centering in text or visuals

    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
    center
    -1.00
    tagHelperRunner
    -0.99
     kasarigan
    -0.85
    Center
    -0.77
    WebServlet
    -0.73
    DoubleQuotes
    -0.72
     ujednoznacz
    -0.70
    OGND
    -0.70
    __((
    -0.69
     Waray
    -0.69
    POSITIVE LOGITS
    .");
    
    0.47
    ."));
    0.46
    eurovision
    0.45
    !")
    
    0.44
    èo
    0.43
     materiaal
    0.42
     veilig
    0.42
     bezit
    0.42
    .")
    
    0.42
     surname
    0.42
    Activations Density 0.058%

    No Known Activations