© 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. 8097
    Prev
    Next
    INDEX
    Explanations

    references to moral or ethical considerations and arguments

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

    Lists of examples or included items

    np_acts-logits-general · gemini-2.0-flash

    listing examples

    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
    AddTagHelper
    -0.55
    ValueStyle
    -0.44
    yarnpkg
    -0.44
     pertes
    -0.43
    classnames
    -0.42
    |}{
    -0.41
    same
    -0.41
    qrstuvwxyz
    -0.40
     izle
    -0.40
    üste
    -0.40
    POSITIVE LOGITS
     things
    1.86
     Things
    1.45
     such
    1.43
     stuff
    1.40
    things
    1.38
    Things
    1.36
     THINGS
    1.36
     cosas
    1.29
     Dinge
    1.25
     coisas
    1.24
    Activations Density 0.349%

    No Known Activations