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. 8784
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "of"

    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
    .
    -0.92
      
    -0.86
     of
    -0.85
     
    -0.82
     and
    -0.82
    ,
    -0.77
     (
    -0.75
     or
    -0.73
    !
    -0.66
     as
    -0.65
    POSITIVE LOGITS
     itſelf
    1.51
     Theſe
    1.47
     Efq
    1.41
     ―――――
    1.39
     myſelf
    1.37
    ſelf
    1.33
    ſelves
    1.32
     ſeveral
    1.30
     Houſe
    1.29
     Majefty
    1.29
    Activations Density 0.063%

    No Known Activations