© 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. 22-GEMMASCOPE-RES-16K
    11. 3256
    Prev
    Next
    INDEX
    Explanations

    questions that are posed in various contexts or discussions

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

    Follows the token "Question" or "question"

    np_acts-logits-general · gemini-2.0-flash

    poses questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gdx
    -0.82
    ſelf
    -0.80
    ſelves
    -0.73
     leçon
    -0.72
     poffible
    -0.70
     myſelf
    -0.70
     Theſe
    -0.69
     ſeveral
    -0.69
     juſ
    -0.69
    empereur
    -0.69
    POSITIVE LOGITS
     posed
    1.00
     raised
    0.76
     mark
    0.75
     реб
    0.74
     marks
    0.72
     answered
    0.70
     unanswered
    0.69
    aire
    0.66
     arise
    0.61
    naires
    0.61
    Activations Density 0.100%

    No Known Activations