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. 60882
    Prev
    Next
    INDEX
    Explanations

    the verb "emphasizes" in various contexts

    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
    ises
    -0.84
     pec
    -0.56
    ates
    -0.56
    джет
    -0.54
    !*\
    -0.53
    tes
    -0.52
    tiga
    -0.52
    tu
    -0.52
     estr
    -0.52
    WebVitals
    -0.52
    POSITIVE LOGITS
    konomi
    0.74
     XCTest
    0.69
    CodeDom
    0.69
     relève
    0.68
    getWriter
    0.67
     quarries
    0.67
     acous
    0.66
     snippetHide
    0.64
    endphp
    0.63
    yaret
    0.63
    Activations Density 0.007%

    No Known Activations