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-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 109703
    Prev
    Next
    INDEX
    Explanations

    references to personal relationships and emotional connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebElementEntity
    -0.63
    AnchorTagHelper
    -0.60
    aktur
    -0.56
     MainAxisSize
    -0.54
    őben
    -0.53
    UnusedPrivate
    -0.52
     Audiodateien
    -0.52
    出版年
    -0.52
     ujednoznacz
    -0.51
    хівовано
    -0.50
    POSITIVE LOGITS
    WindowConstants
    0.41
    butuhkan
    0.41
     triggers
    0.34
    LITERAL
    0.33
    richTextPanel
    0.31
     '\\;'
    0.31
     snippetHide
    0.31
     mixed
    0.30
    WebControls
    0.30
    épend
    0.29
    Activations Density 0.032%

    No Known Activations