© 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. 109295
    Prev
    Next
    INDEX
    Explanations

    instances of the word "highlight" in various forms

    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
     highlight
    -1.09
     highlights
    -0.91
     Highlight
    -0.88
     highlighted
    -0.83
    highlight
    -0.81
    highlights
    -0.79
     Highlights
    -0.78
     highlighting
    -0.76
    Highlight
    -0.75
     HIGHLIGHTS
    -0.73
    POSITIVE LOGITS
    ंदीखरीदारी
    0.47
    +:+
    0.46
    verwijspagina
    0.41
     ſtate
    0.40
     purpoſe
    0.38
    VYMaps
    0.36
     Modular
    0.36
     ब्रेकडाउन
    0.36
     propOrder
    0.36
     invers
    0.35
    Activations Density 0.004%

    No Known Activations