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. 22-GEMMASCOPE-MLP-16K
    6. 15858
    Prev
    Next
    INDEX
    Explanations

    terms related to processing speed and efficiency in computing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_mlp_out
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hentet
    -1.00
    RenderAtEndOf
    -0.85
    expandindo
    -0.83
    tagHelperRunner
    -0.80
     समीक्षाएं
    -0.77
     nahilalakip
    -0.75
    帖最后由
    -0.73
    webElementXpaths
    -0.71
    adaptiveStyles
    -0.71
    writeFieldEnd
    -0.69
    POSITIVE LOGITS
     unbelievable
    1.08
     incredible
    1.08
     extraordinary
    1.02
     astonishing
    1.02
     astounding
    0.99
     amazing
    0.96
     remarkable
    0.94
     unacceptable
    0.92
     phenomenal
    0.91
     alarming
    0.91
    Activations Density 0.484%

    No Known Activations