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. 22-GEMMASCOPE-MLP-16K
    6. 15804
    Prev
    Next
    INDEX
    Explanations

    legal terminology and expressions related to judicial decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_mlp_out
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vœux
    -0.69
     bienfaits
    -0.68
     attentes
    -0.63
     bénéfices
    -0.61
     débats
    -0.60
     épaules
    -0.60
     oreilles
    -0.60
     dieux
    -0.56
     travailleurs
    -0.56
    клопе
    -0.55
    POSITIVE LOGITS
     situations
    1.23
     environments
    1.22
     countries
    1.22
     societies
    1.20
     companies
    1.17
     languages
    1.16
     technologies
    1.14
     scenarios
    1.13
     cases
    1.13
     songs
    1.12
    Activations Density 1.680%

    No Known Activations