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. 4-GEMMASCOPE-MLP-65K
    6. 70
    Prev
    Next
    INDEX
    Explanations

    references to degrees of emotional or situational tension

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_4/width_65k/average_l0_66
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.4.hook_mlp_out
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hyrchwyd
    -0.60
    Filmografia
    -0.56
    ViewFeatures
    -0.56
    lapsingToolbar
    -0.55
    protoimpl
    -0.54
    viewtopic
    -0.54
    Derbyniad
    -0.54
    ournal
    -0.53
    énario
    -0.53
    omitempty
    -0.51
    POSITIVE LOGITS
    RRect
    0.56
    KommentareTeilen
    0.56
    PageRoute
    0.51
    SuccessListener
    0.49
    المناصب
    0.47
     AssemblyProduct
    0.47
    Digitized
    0.45
     оригіналу
    0.45
    írito
    0.45
     INVENTION
    0.44
    Activations Density 0.065%

    No Known Activations