© 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. 24-GEMMASCOPE-RES-16K
    11. 4125
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and concepts related to complex analysis and function theory

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

    complex numbers or analysis

    np_acts-logits-general · gemini-2.0-flash

    complex and imaginary parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.69
    sizeCache
    -0.61
     useAppContext
    -0.60
     Aristi
    -0.58
     odkazy
    -0.58
     AssemblyCulture
    -0.54
    पया
    -0.54
     Mep
    -0.53
     مرئيه
    -0.52
    OGND
    -0.52
    POSITIVE LOGITS
     complex
    1.58
    complex
    1.52
    Complex
    1.51
     Complex
    1.50
    COMPLEX
    1.31
     COMPLEX
    1.29
     complexe
    1.20
     komplex
    1.18
     complexo
    1.16
     kompleks
    1.12
    Activations Density 1.086%

    No Known Activations