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. 4-GEMMASCOPE-MLP-65K
    6. 12
    Prev
    Next
    INDEX
    Explanations

    terms related to building structures and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_4/width_65k/average_l0_66
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.4.hook_mlp_out
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EDEFAULT
    -0.73
    rceil
    -0.68
    ThroughAttribute
    -0.66
    :✨
    -0.65
    Above
    -0.63
     Above
    -0.63
     Up
    -0.62
     publicKey
    -0.60
    avyzd
    -0.60
     tertinggi
    -0.60
    POSITIVE LOGITS
     bottom
    0.82
     down
    0.72
    BorderFactory
    0.69
     lower
    0.69
     lowered
    0.67
     lowering
    0.66
     cellar
    0.65
    DropColumn
    0.65
    Downs
    0.65
    bottom
    0.65
    Activations Density 0.407%

    No Known Activations