© 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. 2-GEMMASCOPE-RES-16K
    11. 15985
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'choose' and related terms indicating decision-making or selection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
    MigrationBuilder
    -0.46
    ♮
    -0.45
    apnews
    -0.43
     iterable
    -0.42
    RegistryLite
    -0.41
     Sel
    -0.41
    WebServlet
    -0.40
     intermittently
    -0.39
    RefreshLayout
    -0.39
    Personensuche
    -0.39
    POSITIVE LOGITS
     choose
    3.36
     choosing
    3.27
    choose
    3.06
     chooses
    3.06
     chose
    3.06
     Choose
    2.94
    Choose
    2.91
     Choosing
    2.88
    choosing
    2.86
    Choosing
    2.81
    Activations Density 0.136%

    No Known Activations