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. 8740
    Prev
    Next
    INDEX
    Explanations

    terms related to magnetic interactions and theoretical models in physics

    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
    ˈ
    -0.53
    =}
    -0.52
    illées
    -0.51
     दर
    -0.50
     kasarigan
    -0.50
     Casserole
    -0.48
    verre
    -0.47
    rän
    -0.46
     State
    -0.46
    Composable
    -0.46
    POSITIVE LOGITS
     acrylique
    0.57
    💼
    0.56
    PreferredItem
    0.55
    BagLayout
    0.55
     recevez
    0.54
    ünster
    0.54
    windowFixed
    0.54
    الإنجليزية
    0.54
     prouve
    0.54
    proken
    0.52
    Activations Density 0.825%

    No Known Activations