© 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. 3-GEMMASCOPE-RES-16K
    11. 2619
    Prev
    Next
    INDEX
    Explanations

    phrases relating to gender roles and family planning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
    CodeAttribute
    -0.81
     propOrder
    -0.81
    ंदीखरीदारी
    -0.80
     Мексичка
    -0.80
    featureID
    -0.78
    enterOuterAlt
    -0.76
    CreateModel
    -0.75
    IsContent
    -0.75
    Rüyada
    -0.74
     useStyles
    -0.73
    POSITIVE LOGITS
     workflows
    0.47
    क्षित
    0.47
     enable
    0.45
    spaceBetween
    0.45
     leveraging
    0.44
     identify
    0.43
    otypes
    0.43
     identifying
    0.43
    flä
    0.43
    يكب
    0.42
    Activations Density 0.924%

    No Known Activations