© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4157
    Prev
    Next
    INDEX
    Explanations

    references to the word "her" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.87
     raiſ
    -0.86
     Houſe
    -0.82
     uſe
    -0.78
     Оно
    -0.77
     purpoſe
    -0.74
     Efq
    -0.74
     cauſe
    -0.73
     pleaſure
    -0.72
     uſed
    -0.70
    POSITIVE LOGITS
     her
    3.01
    her
    2.01
     Her
    1.89
     HER
    1.89
    Her
    1.84
     his
    1.68
    她的
    1.62
     hennes
    1.57
    HER
    1.53
     hers
    1.50
    Activations Density 0.056%

    No Known Activations