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. 109780
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "slip" and its variations

    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
     ModelExpression
    -0.54
     jadx
    -0.52
    expandindo
    -0.51
     Мексичка
    -0.50
     StatefulWidget
    -0.50
    NameInMap
    -0.48
     виправивши
    -0.47
    niająca
    -0.47
    клопе
    -0.44
    Scope
    -0.43
    POSITIVE LOGITS
     externi
    0.41
    AccessFile
    0.36
     Mühl
    0.35
    NUMX
    0.34
     تضيفلها
    0.34
     aha
    0.33
     XNUMX
    0.33
     Thron
    0.33
     elastici
    0.33
     indisponible
    0.32
    Activations Density 0.002%

    No Known Activations