© 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. 4370
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to data manipulation and querying

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

    Code, file types, or programming

    np_acts-logits-general · gemini-2.0-flash

    technical documents and code

    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
     تضيفلها
    -0.87
     становника
    -0.82
    thmus
    -0.60
    __(/*!
    -0.57
    حياته
    -0.56
    ướng
    -0.56
    bundet
    -0.53
    undum
    -0.53
    DebuggerStep
    -0.53
    󠁢
    -0.53
    POSITIVE LOGITS
    دانشنامهٔ
    0.70
    transQ
    0.66
     điện
    0.53
    SqlQuery
    0.51
    jsxFileName
    0.49
    usermodel
    0.49
    ๆ
    0.48
    
    0.48
     railroad
    0.47
     المصرية
    0.47
    Activations Density 0.828%

    No Known Activations