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. 6-GEMMASCOPE-MLP-16K
    6. 209
    Prev
    Next
    INDEX
    Explanations

    instances and variations 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 @ 6-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Of
    -0.70
     Of
    -0.61
    zieć
    -0.60
    EndContext
    -0.59
     OF
    -0.56
     of
    -0.56
    httphttps
    -0.52
    OF
    -0.51
     ent
    -0.51
     Normdatei
    -0.47
    POSITIVE LOGITS
     hObject
    0.69
    
    0.68
     InputDecoration
    0.65
    ($__
    0.63
    lectic
    0.59
    UnsafeEnabled
    0.59
     estekak
    0.54
     chi̍t
    0.53
    SqlClient
    0.52
     appunto
    0.51
    Activations Density 0.138%

    No Known Activations