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. 109802
    Prev
    Next
    INDEX
    Explanations

    instances of the word "never"

    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
     never
    -0.59
     '\\;'
    -0.56
    nunca
    -0.55
    enterOuterAlt
    -0.54
    never
    -0.54
    Vidite
    -0.53
     Never
    -0.53
     esternos
    -0.53
    Never
    -0.50
     nigdy
    -0.50
    POSITIVE LOGITS
     gainera
    0.54
     rapid
    0.36
     RoutedEventArgs
    0.35
     DKI
    0.33
    策
    0.31
    באנגלית
    0.31
     respald
    0.31
     rapida
    0.31
    出版年
    0.30
    tagext
    0.29
    Activations Density 0.001%

    No Known Activations