© 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. 22-GEMMASCOPE-RES-16K
    11. 8322
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions, particularly involving limits and fractional forms

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

    LaTeX math expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical limits and derivatives

    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
     Wikimedijinoj
    -0.90
    ThroughAttribute
    -0.82
     تضيفلها
    -0.79
    ///</
    -0.76
     كومونز
    -0.75
    󠁿
    -0.74
     }}"></
    -0.74
     gynnwys
    -0.73
    Rujuakan
    -0.70
    rawDesc
    -0.70
    POSITIVE LOGITS
     gynhyrchwyd
    0.68
    UserScript
    0.56
    numerusform
    0.55
     تعدى
    0.53
     maternelle
    0.51
     InputDecoration
    0.49
    حوالہ
    0.48
    unggulan
    0.47
    asilan
    0.44
     segü
    0.44
    Activations Density 1.554%

    No Known Activations