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. 1-GEMMASCOPE-MLP-16K
    6. 8960
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming functions and method calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_mlp_out
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.52
     '**
    -0.50
     ویکی‌پدیا
    -0.49
    RSpec
    -0.49
    fsch
    -0.48
    jemah
    -0.47
    ContainerState
    -0.46
    IContainer
    -0.45
     énergé
    -0.44
     financières
    -0.44
    POSITIVE LOGITS
    NUMX
    0.66
     BoxDecoration
    0.65
     transférez
    0.63
    "?>
    0.63
    ParallelGroup
    0.60
    encodeWith
    0.59
    SequentialGroup
    0.59
    enderror
    0.58
    bitur
    0.58
     Muf
    0.57
    Activations Density 0.322%

    No Known Activations