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. 22-GEMMASCOPE-MLP-16K
    6. 15791
    Prev
    Next
    INDEX
    Explanations

    fractions and proportions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_mlp_out
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -1.00
    IntoConstraints
    -1.00
    bootstrapcdn
    -0.90
     CreateTagHelper
    -0.82
    ագրություններ
    -0.73
    RTLD
    -0.73
    AsUp
    -0.72
    twimg
    -0.71
    RTEE
    -0.68
    reportWebVitals
    -0.66
    POSITIVE LOGITS
     saurait
    0.45
    toyage
    0.45
    дравствуйте
    0.45
     Diret
    0.45
    őd
    0.43
    āci
    0.43
    optString
    0.42
     attiv
    0.42
     gái
    0.42
    grenzung
    0.42
    Activations Density 0.088%

    No Known Activations