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-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 109662
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to mathematical classes and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TextAppearance
    -0.37
    いしい
    -0.32
     الشع
    -0.31
    收
    -0.29
    رشف
    -0.29
    الدراسه
    -0.29
    IContainer
    -0.28
    StoreMessageInfo
    -0.27
    LEncoder
    -0.27
     LoggerFactory
    -0.27
    POSITIVE LOGITS
     Portail
    0.51
     ostavi
    0.50
    PREFERRED
    0.49
    CppMethod
    0.48
    Tracce
    0.47
     peluche
    0.47
     مواليد
    0.46
    AndEndTag
    0.46
     незавершена
    0.46
    ########.
    0.46
    Activations Density 1.806%

    No Known Activations