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. 15780
    Prev
    Next
    INDEX
    Explanations

    variations of the term "geo" or "geonomics" related to economic and environmental concepts

    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
     spéciales
    -0.55
    EditorBrowsable
    -0.50
     immédi
    -0.49
     članak
    -0.49
    rosine
    -0.49
     Later
    -0.48
     afterward
    -0.48
    tauscht
    -0.47
     later
    -0.47
    iformes
    -0.47
    POSITIVE LOGITS
     defaultstate
    0.85
    enderror
    0.70
    ंदीखरीदारी
    0.65
    errHandler
    0.59
    ).]
    0.57
    awtextra
    0.56
     незавершена
    0.56
    DotNetBar
    0.56
    تقاوى
    0.55
    httphttps
    0.54
    Activations Density 0.014%

    No Known Activations