© 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. 3-GEMMASCOPE-RES-16K
    11. 10251
    Prev
    Next
    INDEX
    Explanations

    terms related to divinity and significant references to the day "Monday."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gel
    -0.45
    Gel
    -0.45
     amen
    -0.43
     GEL
    -0.43
     equip
    -0.42
    kema
    -0.42
     gels
    -0.42
     NUR
    -0.42
     animator
    -0.42
    GEL
    -0.42
    POSITIVE LOGITS
    multicolumn
    0.62
     commander
    0.59
     Commander
    0.58
    commander
    0.55
    multirow
    0.55
    Commander
    0.51
    Welcome
    0.49
     Commanders
    0.48
    Üdv
    0.47
    Wednesday
    0.47
    Activations Density 0.041%

    No Known Activations