© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 11326
    Prev
    Next
    INDEX
    Explanations

    choices or selection-related actions or terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "choose"

    np_acts-logits-general · gemini-2.0-flash

    making a choice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.98
    AlterField
    -0.85
     bezeichneter
    -0.75
    انيف
    -0.75
    DataAnnotations
    -0.74
     houſe
    -0.70
    tagez
    -0.68
    ioutil
    -0.68
     JpaRepository
    -0.68
    liminaries
    -0.67
    POSITIVE LOGITS
     choices
    0.96
     choice
    0.94
     Choose
    0.92
     choose
    0.92
     chooses
    0.91
     choosing
    0.90
     Choices
    0.88
    choose
    0.88
     Choice
    0.88
     Choosing
    0.86
    Activations Density 0.127%

    No Known Activations