© 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. 1029
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate sequences or actions being followed

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

    "followed by"

    np_acts-logits-general · gemini-2.0-flash

    followed by

    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
     /\.
    -0.67
    WebElementEntity
    -0.60
    NOPQRST
    -0.57
     gennem
    -0.55
    záll
    -0.55
     prostu
    -0.53
     makeStyles
    -0.53
    principalTable
    -0.52
     AssemblyCompany
    -0.51
     Просто
    -0.50
    POSITIVE LOGITS
    OGND
    0.68
     autorytatywna
    0.65
    complexContent
    0.64
    migrationBuilder
    0.62
     nicely
    0.57
     GetEnumerator
    0.56
     كومونز
    0.54
     QName
    0.54
    etted
    0.53
     szóci
    0.52
    Activations Density 0.225%

    No Known Activations