© 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. 109899
    Prev
    Next
    INDEX
    Explanations

    affirmative statements or expressions of certainty

    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
    Certainly
    -0.58
     Certainly
    -0.54
     estekak
    -0.51
    zarchiwizowane
    -0.50
    writeFieldEnd
    -0.49
    참고
    -0.48
     समीक्षक
    -0.48
    GEBURTS
    -0.47
     يتيمه
    -0.47
     noDo
    -0.44
    POSITIVE LOGITS
    getSimpleName
    0.45
    waitKey
    0.41
    queryInterface
    0.39
    dak
    0.35
    brin
    0.34
     asn
    0.34
    addPreferredGap
    0.34
    isis
    0.34
     φ
    0.34
    runners
    0.34
    Activations Density 0.002%

    No Known Activations