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. 60954
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "practiced" 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
    PerformLayout
    -0.91
    enumi
    -0.89
     BoxFit
    -0.88
    mbggenerated
    -0.86
    LEncoder
    -0.84
     Exacts
    -0.81
    enderror
    -0.78
     EconPapers
    -0.77
     @"/
    -0.76
    afficheront
    -0.76
    POSITIVE LOGITS
     blat
    0.56
    himself
    0.53
     Staates
    0.52
     dirinya
    0.52
     imidlertid
    0.51
     ulang
    0.51
    ;';
    0.50
     löytyy
    0.50
    xsi
    0.49
    //}
    
    0.49
    Activations Density 0.004%

    No Known Activations