© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 38191
    Prev
    Next
    INDEX
    Explanations

    references to specific dates, particularly in March

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ../../
    -0.79
     NCS
    -0.77
     Escobar
    -0.73
    kegaard
    -0.73
     Roskov
    -0.70
    creatic
    -0.69
    EDEFAULT
    -0.69
     "../../../
    -0.69
    InjectAttribute
    -0.69
     Cowan
    -0.68
    POSITIVE LOGITS
     March
    1.68
     MARCH
    1.60
    March
    1.60
     Marchand
    1.52
     march
    1.50
    MARCH
    1.45
     Marches
    1.41
    march
    1.35
     marches
    1.30
     Marcell
    1.20
    Activations Density 0.013%

    No Known Activations