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 - 65k
    5. 0-GEMMASCOPE-MLP-65K
    6. 60944
    Prev
    Next
    INDEX
    Explanations

    the word "well" in various contexts

    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-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ValueStyle
    -0.69
    migrationBuilder
    -0.69
     '\\;'
    -0.68
    "]).
    -0.68
    IsMutable
    -0.67
    expandindo
    -0.67
    KEYCODE
    -0.61
    arXiv
    -0.61
     idén
    -0.60
    PMailer
    -0.60
    POSITIVE LOGITS
     pect
    0.55
    Turning
    0.52
     Meksiku
    0.51
     Zaire
    0.50
     secondaires
    0.50
     Trenton
    0.50
     herself
    0.49
     speciation
    0.49
     nakalista
    0.49
     convenable
    0.49
    Activations Density 0.035%

    No Known Activations