© 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. 22-GEMMASCOPE-RES-16K
    11. 2761
    Prev
    Next
    INDEX
    Explanations

    words and structures related to programming functions and parameters

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

    Code-related terms or foreign language words

    np_acts-logits-general · gemini-2.0-flash

    code structure keywords

    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
    (['/
    -0.54
    ['
    -0.48
    ;
    -0.46
     hại
    -0.44
    举
    -0.43
    toria
    -0.42
    ["
    -0.42
     Jorg
    -0.42
    amata
    -0.42
     Lyons
    -0.41
    POSITIVE LOGITS
    पया
    0.78
    initComponents
    0.74
     שוליים
    0.74
    archiviato
    0.72
    WebVitals
    0.69
    ^(@)
    0.69
     Waray
    0.66
     Pingback
    0.65
     AssemblyTitle
    0.65
    rungsseite
    0.63
    Activations Density 0.040%

    No Known Activations