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. 15934
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operations involving variables and numbers

    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
    fiées
    -0.54
     Dichter
    -0.49
    gridx
    -0.45
    ICD
    -0.45
    ณ์
    -0.44
    ristan
    -0.44
    роль
    -0.44
     mechan
    -0.44
     esteja
    -0.43
     européennes
    -0.43
    POSITIVE LOGITS
    WithMany
    0.79
     cherchés
    0.70
    Gambas
    0.69
     ostavi
    0.68
     Approximately
    0.66
     estekak
    0.66
    richTextPanel
    0.66
    Approximately
    0.65
    ThroughAttribute
    0.65
     XXIV
    0.65
    Activations Density 2.214%

    No Known Activations