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. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16346
    Prev
    Next
    INDEX
    Explanations

    specific mentions of materials and their qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.56
     EconPapers
    -0.55
     ModelExpression
    -0.51
    addCriterion
    -0.47
     metálico
    -0.46
     AssemblyCulture
    -0.45
     Edelstahl
    -0.43
     namanya
    -0.41
    SizeF
    -0.40
     edelstahl
    -0.40
    POSITIVE LOGITS
    製の
    0.65
    製
    0.65
    covered
    0.56
     coated
    0.55
     construction
    0.54
     texture
    0.54
     clad
    0.52
     covered
    0.50
     tubing
    0.48
     lining
    0.48
    Activations Density 0.626%

    No Known Activations