© 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. 10494
    Prev
    Next
    INDEX
    Explanations

    references to a female subject, particularly the word "She" in various forms

    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
    IntoConstraints
    -0.51
    colhead
    -0.47
    tangentMode
    -0.46
     '\\;'
    -0.45
    råd
    -0.42
    Adopt
    -0.42
     Coloring
    -0.42
     Adop
    -0.42
     exceptions
    -0.42
     SUNY
    -0.40
    POSITIVE LOGITS
     She
    0.60
    Autoritní
    0.60
     из
    0.54
    WebServlet
    0.50
    She
    0.50
    InstanceState
    0.50
     thermal
    0.47
    Из
    0.47
    ⓧ
    0.46
     Knock
    0.45
    Activations Density 0.035%

    No Known Activations