© 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. 6816
    Prev
    Next
    INDEX
    Explanations

    expressions involving mathematical or logical operations

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

    The plus sign before a variable name

    np_acts-logits-general · gemini-2.0-flash

    string concatenation operator

    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
    ">—
    -0.72
    XmlAccessType
    -0.72
     linkovi
    -0.67
    Autoritní
    -0.64
     uſed
    -0.64
    InvalidProtocol
    -0.62
     Monfieur
    -0.62
    ſelves
    -0.62
     [](
    -0.61
     محفوظة
    -0.60
    POSITIVE LOGITS
    getDescriptor
    0.52
     Chwiliwch
    0.47
    //:
    0.46
     '/'
    0.44
     :
    0.43
     CascadeType
    0.43
    rzost
    0.43
    "/
    0.42
    complexContent
    0.41
    corbic
    0.41
    Activations Density 0.049%

    No Known Activations