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. 208
    Prev
    Next
    INDEX
    Explanations

    words that indicate abundance or excessiveness

    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
     auch
    -0.58
    BeginContext
    -0.53
     ook
    -0.52
     للمعارف
    -0.52
     Auch
    -0.50
    ด้
    -0.50
     tambin
    -0.48
     również
    -0.47
     également
    -0.46
    jarkan
    -0.45
    POSITIVE LOGITS
    SourceChecksum
    0.72
    LookAnd
    0.67
     Lightboxes
    0.67
    PageModule
    0.66
    HasForeignKey
    0.65
     newOwner
    0.65
    WindowConstants
    0.61
    makeConstraints
    0.61
    hemiah
    0.61
     فريبيس
    0.58
    Activations Density 0.168%

    No Known Activations