© 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. 7081
    Prev
    Next
    INDEX
    Explanations

    various types of code syntax and symbols

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

    Code diffs, stack traces, and file paths

    np_acts-logits-general · gemini-2.0-flash

    biological state or technical notation

    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
     AssemblyTitle
    -0.73
    elemField
    -0.57
    govina
    -0.53
     mind
    -0.50
    localPosition
    -0.49
    Câu
    -0.48
     range
    -0.48
    \|_{\
    -0.47
    Poloha
    -0.44
     giù
    -0.43
    POSITIVE LOGITS
     disambiguazione
    1.01
    Tikang
    0.95
    Hochspringen
    0.87
     дописавши
    0.82
    ScopeManager
    0.80
     utafitiHapana
    0.78
    Diwedd
    0.71
    Bakgrunnsstoff
    0.69
     Longfellow
    0.68
     jsPsych
    0.67
    Activations Density 0.180%

    No Known Activations