© 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. 3731
    Prev
    Next
    INDEX
    Explanations

    occurrences of jQuery selectors and related identifiers in the document structure

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

    jQuery selectors using '$(' or '$("#'

    np_acts-logits-general · gemini-2.0-flash

    jQuery selectors and HTML elements

    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
     userRepository
    -0.53
    She
    -0.50
    DateField
    -0.49
     She
    -0.47
    orith
    -0.46
     TimeUnit
    -0.45
    So
    -0.45
     Termine
    -0.45
    ˜
    -0.45
     So
    -0.44
    POSITIVE LOGITS
    featureID
    0.85
     fubject
    0.82
     myſelf
    0.81
    GEBURTSDATUM
    0.81
     purpoſe
    0.79
    tagext
    0.76
     leaſt
    0.75
    IContainer
    0.75
    ftagPool
    0.74
     cauſe
    0.74
    Activations Density 0.202%

    No Known Activations