© 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. 961
    Prev
    Next
    INDEX
    Explanations

    specific quantities and details regarding scientific measurements and experimental protocols

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

    Values related to volume/concentration (µ, uL, etc.)

    np_acts-logits-general · gemini-2.0-flash

    micrometers and micro-units

    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
     Ouverture
    -0.56
    indow
    -0.54
    MessageInfo
    -0.51
    msgTypes
    -0.49
    Abit
    -0.48
    имость
    -0.48
     Flat
    -0.48
    endwhile
    -0.48
    kWh
    -0.48
     lives
    -0.47
    POSITIVE LOGITS
    tagHelperRunner
    0.73
     microns
    0.73
     mic
    0.73
     micron
    0.70
     micro
    0.69
    micro
    0.68
    μ
    0.67
     μ
    0.67
    micron
    0.67
    mic
    0.66
    Activations Density 0.719%

    No Known Activations