© 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. 34-GEMMASCOPE-RES-16K
    11. 6759
    Prev
    Next
    INDEX
    Explanations

    instances of the word "my" and its variations to indicate possession or personal reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     meille
    -0.55
     conosco
    -0.52
     respectively
    -0.52
     natin
    -0.48
     yourselves
    -0.46
     autorytatywna
    -0.45
     powinna
    -0.44
    EndGlobalSection
    -0.43
    Jeografia
    -0.43
     JpaRepository
    -0.42
    POSITIVE LOGITS
     my
    1.06
     myself
    0.83
     mijn
    0.80
    opic
    0.80
     meinem
    0.79
    我的
    0.77
     wife
    0.74
     dad
    0.74
     mom
    0.73
     miei
    0.73
    Activations Density 0.139%

    No Known Activations