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. 61035
    Prev
    Next
    INDEX
    Explanations

    monetary symbols and related notations

    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
    #+#
    -0.64
    enumi
    -0.60
    PerformLayout
    -0.52
     @"/
    -0.49
    omla
    -0.46
    issau
    -0.46
     Par
    -0.45
     .
    -0.45
     pavo
    -0.44
    mistak
    -0.43
    POSITIVE LOGITS
     disparu
    0.74
     theſe
    0.71
     étoit
    0.69
     colorés
    0.69
    ேன்
    0.69
     Theres
    0.68
     itſelf
    0.68
     himſelf
    0.68
     étoient
    0.67
     auroit
    0.66
    Activations Density 0.092%

    No Known Activations