© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13304
    Prev
    Next
    INDEX
    Explanations

    Java programming constructs and elements related to threading

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

    Code snippets or mathematical notation

    np_acts-logits-general · gemini-2.0-flash

    special characters followed by code or math

    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
    transQ
    -0.61
    WriteTagHelper
    -0.60
    writeField
    -0.56
     referenties
    -0.55
     //$
    -0.54
    tonode
    -0.54
     betweenstory
    -0.53
    utilisons
    -0.52
     aload
    -0.51
    willReturn
    -0.49
    POSITIVE LOGITS
    Personendaten
    0.63
     EconPapers
    0.62
    AddTagHelper
    0.58
     surla
    0.56
     GenerationType
    0.56
     FetchType
    0.55
    AnchorStyles
    0.54
     Dea
    0.53
    IMIENTO
    0.52
     Wikimédia
    0.52
    Activations Density 0.029%

    No Known Activations