© 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. 1344
    Prev
    Next
    INDEX
    Explanations

    words related to scientific measurements and assessments in research studies

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

    followed by scientific or research concepts

    np_acts-logits-general · gemini-2.0-flash

    results and documented findings

    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
     Afterward
    -0.94
     gotten
    -0.91
    Analyzing
    -0.81
     oftentimes
    -0.77
     colorful
    -0.76
    endphp
    -0.76
     mold
    -0.76
    Билгалдахарш
    -0.75
    favorite
    -0.74
     folks
    -0.74
    POSITIVE LOGITS
    Whilst
    1.03
     Whilst
    1.02
     whilst
    0.95
     envisage
    0.78
     envisaged
    0.77
     programme
    0.73
    cognised
    0.73
    initialise
    0.73
     recognised
    0.73
     commonest
    0.72
    Activations Density 1.656%

    No Known Activations