© 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. 10489
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or calculations, particularly those related to derivatives and products

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

    Numbers extracted from math problems

    np_acts-logits-general · gemini-2.0-flash

    mathematical calculations

    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
     oprot
    -0.93
     ExecuteAsync
    -0.78
     jScrollPane
    -0.74
     propOrder
    -0.74
    complexContent
    -0.73
    CompleteListener
    -0.73
     متعلقه
    -0.71
    AnimationsModule
    -0.68
    rungsseite
    -0.67
    .*")]
    -0.65
    POSITIVE LOGITS
    principalColumn
    0.51
    issan
    0.48
     fer
    0.47
     follow
    0.47
    ORES
    0.46
    镇
    0.46
    restrial
    0.45
     alla
    0.44
     alien
    0.44
    apiKey
    0.44
    Activations Density 0.986%

    No Known Activations