© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 7369
    Prev
    Next
    INDEX
    Explanations

    references to complexity in various contexts

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

    Followed by words describing intricate systems or analysis

    np_acts-logits-general · gemini-2.0-flash

    complex things or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     isotropic
    -0.71
    serviceWorker
    -0.66
     eosin
    -0.62
     presidenta
    -0.59
    istiwa
    -0.57
     motivadoras
    -0.57
     sensazione
    -0.57
    psw
    -0.57
    khidmatan
    -0.56
     feltro
    -0.56
    POSITIVE LOGITS
     complex
    1.60
     Complex
    1.46
    XmlAccessType
    1.43
    complex
    1.38
    COMPLEX
    1.36
    Complex
    1.34
     COMPLEX
    1.34
     complexity
    1.20
     intricate
    1.19
     complexities
    1.18
    Activations Density 0.191%

    No Known Activations