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. 61041
    Prev
    Next
    INDEX
    Explanations

    terms related to legal rights and entitlements

    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
     للمعارف
    -0.65
     aberration
    -0.60
     Kese
    -0.59
    ய்ய
    -0.58
     abstracts
    -0.57
    المناصب
    -0.56
     Proving
    -0.56
    Condol
    -0.55
    ActionMode
    -0.55
     noDo
    -0.54
    POSITIVE LOGITS
     femininas
    0.66
     vectorielles
    0.61
     économies
    0.54
     Monfieur
    0.53
     générations
    0.53
     Shakspeare
    0.52
     artificiales
    0.52
     internacionais
    0.52
     BorderSide
    0.51
     felicità
    0.51
    Activations Density 0.137%

    No Known Activations