© 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. 36-GEMMASCOPE-RES-16K
    11. 5361
    Prev
    Next
    INDEX
    Explanations

    mentions of familial relationships and dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     daughter
    -0.96
     filha
    -0.95
     hija
    -0.91
     Daughter
    -0.85
     daughters
    -0.85
     hijas
    -0.85
    女儿
    -0.84
    daughter
    -0.84
    Daughter
    -0.83
     дочь
    -0.80
    POSITIVE LOGITS
     boy
    2.28
    boy
    1.95
     Boy
    1.89
     boys
    1.86
    Boy
    1.80
    boys
    1.70
     BOY
    1.70
    BOY
    1.62
     Boys
    1.59
    Boys
    1.59
    Activations Density 0.310%

    No Known Activations