© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 5712
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and concepts related to integration

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

    Integration, integrals, and related mathematical operations

    np_acts-logits-general · gemini-2.0-flash

    integration and integrals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebServlet
    -0.78
     nahilalakip
    -0.76
     reaſon
    -0.64
    Predecesor
    -0.63
    stdc
    -0.62
     Reichen
    -0.62
     Noi
    -0.60
    lique
    -0.59
    (!__
    -0.59
     Âge
    -0.57
    POSITIVE LOGITS
     integration
    1.74
     integrate
    1.56
     integrals
    1.53
     Integration
    1.51
    integration
    1.49
     integral
    1.48
     integrating
    1.46
    Integr
    1.46
    Integration
    1.46
     INTEGR
    1.42
    Activations Density 1.016%

    No Known Activations