© 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. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 8311
    Prev
    Next
    INDEX
    Explanations

    the word "mit" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.66
    
    -0.54
    internalType
    -0.48
    oneofs
    -0.48
    findpost
    -0.47
     verlang
    -0.46
    rrggbb
    -0.44
     okuyayım
    -0.43
    featureID
    -0.41
    MigrationBuilder
    -0.41
    POSITIVE LOGITS
    mit
    1.38
     Mit
    1.35
     mit
    1.29
    Mit
    1.26
     Mitchell
    1.03
    Mitchell
    0.98
     MITCHELL
    0.89
    MIT
    0.88
     permit
    0.82
    mits
    0.81
    Activations Density 0.320%

    No Known Activations