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. 8913
    Prev
    Next
    INDEX
    Explanations

    instances of the word "carry."

    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
     carry
    -2.72
    carry
    -2.53
     carried
    -2.47
     Carry
    -2.45
     carrying
    -2.41
     carries
    -2.41
    Carry
    -2.39
     CARRY
    -2.38
     Carrying
    -2.23
    carried
    -2.22
    POSITIVE LOGITS
    faatkan
    0.56
     propOrder
    0.49
    SUPPLEMENT
    0.49
     onBind
    0.48
    LEEP
    0.47
    tigheter
    0.47
    ">'.$
    0.46
     initComponents
    0.46
     Facility
    0.45
    ,–
    0.45
    Activations Density 0.138%

    No Known Activations