© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 110236
    Prev
    Next
    INDEX
    Explanations

    separate code blocks or empty lines in programming syntax

    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
    rungsseite
    -0.91
     الحره
    -0.86
     autorytatywna
    -0.85
    новниш
    -0.85
     ब्रेकडाउन
    -0.84
     ligiloj
    -0.81
     للاسماء
    -0.80
    tagHelperRunner
    -0.77
    fjspx
    -0.77
     ModelExpression
    -0.77
    POSITIVE LOGITS
    ,
    0.33
     
    0.32
    <i>
    0.29
     “
    0.29
    ViewImports
    0.28
    ↵
    0.28
     i
    0.28
    The
    0.28
     The
    0.28
    0.27
    Activations Density 0.024%
    No Known Activations