© 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. 1311
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and their components in formal notation

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

    Mathematical summation notation

    np_acts-logits-general · gemini-2.0-flash

    mathematical summation

    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
    abestanden
    -0.69
    XmlAccessType
    -0.67
    ніципалі
    -0.59
     cracker
    -0.59
     Cracker
    -0.59
    Vorlage
    -0.57
    andidate
    -0.54
    ]--;
    -0.53
     TimeUnit
    -0.52
     itſelf
    -0.52
    POSITIVE LOGITS
    sum
    1.75
     sum
    1.72
    ∑
    1.47
     Sum
    1.46
    Sum
    1.45
    SUM
    1.39
     SUM
    1.36
     summation
    1.33
     sums
    1.17
     summing
    1.16
    Activations Density 0.992%

    No Known Activations