© 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. 3985
    Prev
    Next
    INDEX
    Explanations

    the word "chose" and its variations in various contexts

    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
    bundled
    -0.57
    bund
    -0.56
    fuck
    -0.56
    libft
    -0.55
    suck
    -0.55
    icky
    -0.55
    izr
    -0.55
    Fuck
    -0.54
     fucked
    -0.54
    chok
    -0.54
    POSITIVE LOGITS
     chose
    0.69
     opts
    0.65
     chofe
    0.60
     choosing
    0.59
     brief
    0.57
     Focus
    0.57
     chosen
    0.56
     opted
    0.56
     opt
    0.53
    Choosing
    0.53
    Activations Density 0.262%

    No Known Activations