© 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. 12326
    Prev
    Next
    INDEX
    Explanations

    elements and properties related to system programming and UI design in Windows Forms applications

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

    Code snippets or file paths

    np_acts-logits-general · gemini-2.0-flash

    show percentage or number

    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
    vet
    -0.53
    com
    -0.49
    illi
    -0.48
    QName
    -0.47
     [
    -0.46
    obj
    -0.46
    ['
    -0.46
     obj
    -0.45
    qu
    -0.44
    IBOutlet
    -0.44
    POSITIVE LOGITS
     beginnetje
    0.82
    extAlignment
    0.78
     виправивши
    0.77
    LookAnd
    0.77
    setVerticalGroup
    0.76
    StructEnd
    0.70
    Tikang
    0.67
     pinulongan
    0.67
     whoſe
    0.67
     tartalomajánló
    0.66
    Activations Density 0.020%

    No Known Activations