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. 109716
    Prev
    Next
    INDEX
    Explanations

    terms related to phytoremediation and the study of microorganisms in environmental contexts

    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
    corrhi
    -0.49
    phytes
    -0.41
     phy
    -0.39
    ophyta
    -0.37
    ุป
    -0.35
    ophytes
    -0.35
     circun
    -0.35
    SaveChangesAsync
    -0.34
     경
    -0.33
    uxxxx
    -0.33
    POSITIVE LOGITS
    GOTREF
    0.59
    ValueStyle
    0.59
    +:+
    0.56
     zwiſchen
    0.56
     שוליים
    0.52
     erſt
    0.50
     مرئيه
    0.48
     ſelbſt
    0.48
    ugia
    0.47
    SourceChecksum
    0.47
    Activations Density 0.019%

    No Known Activations