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. 18-GEMMASCOPE-MLP-65K
    6. 73
    Prev
    Next
    INDEX
    Explanations

    specific species names, especially endemic plants and animals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_18/width_65k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.18.hook_mlp_out
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ')")
    -0.72
    __);
    -0.54
    ########.
    -0.50
     tartalomajánló
    -0.50
     beasts
    -0.49
     Josephus
    -0.48
     beetles
    -0.47
     eruption
    -0.45
     myrtle
    -0.45
    出版年
    -0.45
    POSITIVE LOGITS
     calendriers
    0.65
    Демографія
    0.57
     Mahan
    0.55
     Кубка
    0.54
     ویکی‌پدی
    0.54
    oa̍t
    0.54
    олові
    0.52
    ISupport
    0.52
    չ
    0.52
     légales
    0.50
    Activations Density 0.280%

    No Known Activations