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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 4840
    Prev
    Next
    INDEX
    Explanations

    instances of the word "might" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ollectionView
    -0.98
     ECA
    -0.89
     IFA
    -0.85
     Breen
    -0.84
    quelize
    -0.84
     Lipa
    -0.80
     Placer
    -0.79
    তথ্যসূত্র
    -0.79
    CardHeader
    -0.78
    клопе
    -0.77
    POSITIVE LOGITS
     might
    1.22
     MIGHT
    1.20
     Might
    1.16
    might
    1.14
    Might
    1.11
     would
    1.02
     WOULD
    0.93
     could
    0.84
     Would
    0.81
    ght
    0.81
    Activations Density 0.047%

    No Known Activations