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 - 16k
    5. 6-GEMMASCOPE-MLP-16K
    6. 213
    Prev
    Next
    INDEX
    Explanations

    words related to graphic design and office software tools

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    enderror
    -0.79
    HtmlAttribute
    -0.77
    expandindo
    -0.77
     Paglinawan
    -0.76
     estekak
    -0.73
     GeoNames
    -0.68
    ContentAsync
    -0.67
    HostException
    -0.67
    MigrationBuilder
    -0.67
    ViewById
    -0.66
    POSITIVE LOGITS
     
    0.47
     Land
    0.44
    resizingMask
    0.43
    oten
    0.42
    fromCharCode
    0.41
     roll
    0.41
     T
    0.39
    ing
    0.38
     levantó
    0.38
    Land
    0.37
    Activations Density 0.337%

    No Known Activations