© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 16093
    Prev
    Next
    INDEX
    Explanations

    data presenting numerical results or metrics related to health conditions or treatments

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

    Fractions. e.g., "x/y" or "x of y"

    np_acts-logits-general · gemini-2.0-flash

    proportions and counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -1.01
     utafitiHapana
    -0.81
    Personensuche
    -0.78
     насељу
    -0.72
     متعلقه
    -0.71
     purpoſe
    -0.66
    StoryboardSegue
    -0.66
     myſelf
    -0.65
     Biôgrafia
    -0.65
    UserScript
    -0.63
    POSITIVE LOGITS
     out
    1.93
    out
    1.35
     outta
    1.16
     Out
    1.08
    Out
    1.04
     OUT
    1.01
     из
    1.00
     מתוך
    0.94
     among
    0.81
     uit
    0.78
    Activations Density 0.493%

    No Known Activations