© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15916
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands and document formatting elements

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

    LaTeX commands or code snippets

    np_acts-logits-general · gemini-2.0-flash

    LaTeX commands and syntax

    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
     surla
    -0.53
    Kontrola
    -0.53
    amientos
    -0.48
    TestingModule
    -0.48
     ditutup
    -0.48
     setuju
    -0.48
     graag
    -0.47
    toHexString
    -0.47
    ServletException
    -0.47
     hyö
    -0.47
    POSITIVE LOGITS
    Autoritní
    0.91
    AddTagHelper
    0.83
    <?
    0.73
    [];
    
    0.72
    ()");
    0.71
    )";
    
    0.70
    "],
    
    0.69
    "},
    
    0.69
    }],
    
    0.69
    %";
    0.68
    Activations Density 0.021%

    No Known Activations