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. 0-GEMMASCOPE-MLP-16K
    6. 8
    Prev
    Next
    INDEX
    Explanations

    conditional verbs indicating possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "could" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     could
    -2.61
    could
    -2.05
     Could
    -1.86
    Could
    -1.85
     COULD
    -1.42
     podría
    -1.34
     könnte
    -1.27
     podrían
    -1.26
     poderia
    -1.23
     könnten
    -1.20
    POSITIVE LOGITS
    contentLoaded
    1.20
     hObject
    0.96
    :✨
    0.94
     AssemblyCulture
    0.87
    ContentAsync
    0.80
     ivelany
    0.79
     nahilalakip
    0.77
    IUrlHelper
    0.76
     تضيفلها
    0.76
     ErrIntOverflow
    0.76
    Activations Density 0.300%

    No Known Activations