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. 0-GEMMASCOPE-MLP-16K
    6. 18
    Prev
    Next
    INDEX
    Explanations

    symbols and formatting related to programming or code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical or programming-related notations and elements

    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-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    +:+
    -0.64
    ollectionView
    -0.63
    igshid
    -0.59
    GraphicsUnit
    -0.54
    RefNanny
    -0.52
    bootstrapcdn
    -0.50
    |}{}
    -0.48
    ogli
    -0.48
    ̀nh
    -0.48
     autorytatywna
    -0.47
    POSITIVE LOGITS
     JpaRepository
    0.78
     AssemblyTitle
    0.77
    featureID
    0.76
     SwiftUI
    0.73
    ThroughAttribute
    0.65
    DebuggerNonUser
    0.65
    migrationBuilder
    0.64
    `;
    
    0.62
    GEBURTSDATUM
    0.59
    interface
    0.57
    Activations Density 0.701%

    No Known Activations