© 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. 1273
    Prev
    Next
    INDEX
    Explanations

    code structures and programming operations

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

    Code syntax, specifically colons and equals signs

    np_acts-logits-general · gemini-2.0-flash

    function after colon or equals

    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
     acaba
    -0.48
    нении
    -0.47
     reservas
    -0.43
    <bos>
    -0.40
    ja
    -0.40
     сло
    -0.40
    여
    -0.40
     كومونز
    -0.39
     trots
    -0.38
    面的
    -0.37
    POSITIVE LOGITS
     function
    1.60
    function
    1.52
    LookAnd
    1.11
     AssemblyCulture
    0.99
     propOrder
    0.97
    queryInterface
    0.94
    Datuak
    0.94
     FUNCTION
    0.91
     Function
    0.90
    函数
    0.89
    Activations Density 0.136%

    No Known Activations