© 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. 13330
    Prev
    Next
    INDEX
    Explanations

    concepts related to self-organization and collective behavior in active systems

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

    Self-organization and emergent processes

    np_acts-logits-general · gemini-2.0-flash

    complex systems dynamics fractals chaos

    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
     nghiệp
    -0.58
    InSection
    -0.56
    PreExecute
    -0.49
    mybatisplus
    -0.47
     оригіналу
    -0.47
     commerciaux
    -0.47
     Schmer
    -0.46
    Thunk
    -0.46
     sensazione
    -0.45
     commerciali
    -0.45
    POSITIVE LOGITS
     fractal
    0.74
     self
    0.68
    chaos
    0.64
     chaos
    0.63
    ólica
    0.63
     chaotic
    0.63
     dynamics
    0.61
     attra
    0.60
     cellular
    0.59
     evolution
    0.59
    Activations Density 1.719%

    No Known Activations