© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 5830
    Prev
    Next
    INDEX
    Explanations

    references to nighttime or evening activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    暗
    -0.46
     EconPapers
    -0.43
     boosters
    -0.42
     dwar
    -0.42
     Hunter
    -0.40
    witcher
    -0.40
     INCORPOR
    -0.40
    しかったです
    -0.40
     utafitiHapana
    -0.39
    locked
    -0.39
    POSITIVE LOGITS
     nights
    1.21
     Nights
    1.00
     evenings
    0.96
    Nights
    0.90
    nights
    0.82
     mornings
    0.79
     nuits
    0.70
     afternoons
    0.69
     noches
    0.66
    /******/
    0.52
    Activations Density 0.125%

    No Known Activations