© 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. 11665
    Prev
    Next
    INDEX
    Explanations

    code-related terms and constructs, particularly in programming and data structure contexts

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

    Java code, after a number of angle brackets

    np_acts-logits-general · gemini-2.0-flash

    java code and chinese messages

    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
    expandindo
    -0.69
    uxxxx
    -0.66
    protoimpl
    -0.64
    Controllo
    -0.63
    Autoritní
    -0.59
     Wikispecies
    -0.59
    utilisons
    -0.59
    SharedDtor
    -0.59
    GraphicsUnit
    -0.58
     "..\..\
    -0.58
    POSITIVE LOGITS
    </
    2.20
    )</
    1.66
    .</
    1.65
    }</
    1.56
    ;</
    1.48
    "></
    1.48
    !</
    1.43
    }}</
    1.38
    ?</
    1.37
    [/
    1.35
    Activations Density 0.294%

    No Known Activations