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. 8873
    Prev
    Next
    INDEX
    Explanations

    instances of significant actions or concepts

    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
    labelledby
    -0.64
     africaine
    -0.61
     LCCN
    -0.58
    waitKey
    -0.57
     kılıf
    -0.55
     MessageBoxIcon
    -0.55
     tué
    -0.54
    الحياه
    -0.54
     sanguí
    -0.52
     mapStateToProps
    -0.52
    POSITIVE LOGITS
     Réponses
    0.68
    SBATCH
    0.58
    elan
    0.54
    IntOverflow
    0.51
    iastical
    0.49
    andinavia
    0.49
    ilitation
    0.48
    etsu
    0.48
    crollView
    0.48
     down
    0.48
    Activations Density 0.532%

    No Known Activations