© 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. 0-GEMMASCOPE-RES-16K
    11. 6747
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of the suffix 'Jr'

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ſelben
    -0.92
    <unused43>
    -0.89
    <unused41>
    -0.89
    ſammen
    -0.88
    <unused23>
    -0.88
    [@BOS@]
    -0.88
    <unused8>
    -0.87
    <unused14>
    -0.87
    <unused3>
    -0.87
    <pad>
    -0.87
    POSITIVE LOGITS
     Jr
    0.83
     Sr
    0.81
    Sr
    0.62
     Junior
    0.60
     sr
    0.59
     Senior
    0.58
    Jr
    0.52
     jr
    0.49
     JR
    0.47
     Con
    0.44
    Activations Density 0.272%

    No Known Activations