© 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. 5651
    Prev
    Next
    INDEX
    Explanations

    calculations and mathematical expressions related to measurements and comparisons

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

    Following words in math problems or theorems

    np_acts-logits-general · gemini-2.0-flash

    mathematical equations and problems

    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
     Whilst
    -0.88
    Whilst
    -0.80
     Amongst
    -0.74
     optimise
    -0.69
    ConstraintMaker
    -0.67
    Ещё
    -0.65
     realising
    -0.64
     optimised
    -0.64
     realised
    -0.63
     whilst
    -0.63
    POSITIVE LOGITS
    NUMX
    0.85
    '],
    
    0.75
     $\$
    0.73
     يتيمه
    0.71
    "],
    
    0.70
    ')";
    0.70
     "];
    0.68
    .";
    
    0.68
    )";
    
    0.67
    "]
    
    0.66
    Activations Density 0.084%

    No Known Activations