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. 109746
    Prev
    Next
    INDEX
    Explanations

    references to the Mozilla organization or its projects

    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
     Mozilla
    -1.05
    mozilla
    -0.97
    Mozilla
    -0.95
    moz
    -0.91
     Moz
    -0.82
    Moz
    -0.78
     moz
    -0.66
     mo
    -0.50
     SIAM
    -0.45
    êncio
    -0.44
    POSITIVE LOGITS
     PeEnEo
    0.55
    AndEndTag
    0.53
    oredCriteria
    0.50
    copg
    0.49
     Administrativna
    0.48
    uxxxx
    0.48
    Демографія
    0.47
    ніципа
    0.46
     الرياضيه
    0.46
     propOrder
    0.46
    Activations Density 0.001%

    No Known Activations