© 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. 14992
    Prev
    Next
    INDEX
    Explanations

    structured programming language elements, particularly pertaining to classes and properties

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

    Tokens followed by "get"

    np_acts-logits-general · gemini-2.0-flash

    sitting on

    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
     Partagez
    -0.63
    RegressionTest
    -0.59
     Szk
    -0.57
     IndexError
    -0.55
     scolaires
    -0.55
     humaines
    -0.55
    Rüyada
    -0.54
    rungsseite
    -0.54
     xmm
    -0.54
     navideñas
    -0.54
    POSITIVE LOGITS
     get
    0.76
     set
    0.72
    get
    0.57
    Архівовано
    0.56
    archiviato
    0.55
    eronau
    0.53
    ERTY
    0.52
    AxisAlignment
    0.50
     Mao
    0.48
    cherichia
    0.48
    Activations Density 0.018%

    No Known Activations