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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 109433
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conflict or inconsistency in arguments or positions

    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
    BibitemShut
    -0.59
     estekak
    -0.57
    Diwedd
    -0.57
     ब्रेकडाउन
    -0.57
    typeorm
    -0.55
     '{@
    -0.49
    MessageTagHelper
    -0.49
     BoxFit
    -0.49
    SpringRunner
    -0.48
    tifications
    -0.47
    POSITIVE LOGITS
    뀔
    0.41
    expandindo
    0.40
    matchCondition
    0.39
     useContext
    0.38
    localctx
    0.34
    endmodule
    0.34
    DockStyle
    0.33
    チール
    0.32
     resourceCulture
    0.32
    UserScript
    0.32
    Activations Density 0.030%

    No Known Activations