© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3142
    Prev
    Next
    INDEX
    Explanations

    sentences that express collective experiences or observations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     conmigo
    -1.28
     comigo
    -1.03
     mnie
    -0.71
     me
    -0.70
     benim
    -0.69
     Itself
    -0.68
    私に
    -0.67
     мне
    -0.66
     мной
    -0.66
    ándome
    -0.66
    POSITIVE LOGITS
     ourselves
    2.22
     our
    1.30
     можем
    1.08
     наших
    1.06
    我們的
    1.05
    我们的
    1.03
     naszych
    0.99
     nossos
    0.99
     nossas
    0.95
     naše
    0.95
    Activations Density 1.038%

    No Known Activations