© 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. 4738
    Prev
    Next
    INDEX
    Explanations

    phrases related to hormonal effects and behavior dynamics

    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
     COVID
    -1.10
     covid
    -1.06
     Covid
    -1.01
    covid
    -1.01
    COVID
    -0.97
     pandemic
    -0.91
    Covid
    -0.90
     $"{
    -0.89
     🥲
    -0.87
     https
    -0.87
    POSITIVE LOGITS
     idéia
    0.99
     = 
    0.90
    berdayakan
    0.85
     iPod
    0.83
     ipod
    0.81
     daß
    0.78
     xrange
    0.78
    myspace
    0.76
     Arxivat
    0.76
     Orissa
    0.75
    Activations Density 1.320%

    No Known Activations