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. 0-GEMMASCOPE-MLP-16K
    6. 56
    Prev
    Next
    INDEX
    Explanations

    function definitions in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    function declarations and definitions in programming code

    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-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    void
    -1.20
    while
    -0.72
    where
    -0.72
    why
    -0.69
    which
    -0.69
     виправивши
    -0.66
    tanleria
    -0.63
    just
    -0.63
    when
    -0.60
    you
    -0.59
    POSITIVE LOGITS
    URLException
    0.74
     StringTokenizer
    0.73
    setopt
    0.69
    BrowserModule
    0.69
    HtmlAttribute
    0.69
    principalTable
    0.68
    addGap
    0.67
    antart
    0.67
    sqcup
    0.66
    Javadoc
    0.66
    Activations Density 0.067%

    No Known Activations