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. 1-GEMMASCOPE-MLP-16K
    6. 8901
    Prev
    Next
    INDEX
    Explanations

    function-related terminology in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_mlp_out
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    func
    -2.00
     func
    -1.55
    Func
    -0.93
     Func
    -0.77
    iNdEx
    -0.70
    FUNC
    -0.68
    funcs
    -0.67
     functional
    -0.60
     Functional
    -0.59
    Функ
    -0.57
    POSITIVE LOGITS
    QMetaType
    0.65
    findpost
    0.52
     estekak
    0.52
     eleições
    0.52
    AddHtmlAttribute
    0.51
    StoryboardSegue
    0.48
    getColumnIndex
    0.48
    endforeach
    0.47
    īm
    0.47
     pregunto
    0.47
    Activations Density 0.093%

    No Known Activations