© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8102
    Prev
    Next
    INDEX
    Explanations

    words related to simulation and modeling

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

    "Sim", "Sims", and related terms (simulation, simpler, simplex)

    np_acts-logits-general · gemini-2.0-flash

    simulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rosse
    -0.43
     provisoire
    -0.41
     vuestro
    -0.40
     vettoriale
    -0.40
    płat
    -0.39
     íntegra
    -0.39
     المعيارى
    -0.39
     vuestros
    -0.38
     Opfer
    -0.38
     Erster
    -0.38
    POSITIVE LOGITS
     Sim
    0.95
    Sim
    0.82
    SIM
    0.68
     sim
    0.67
     Simulator
    0.66
     SIM
    0.66
     Simulation
    0.62
    sim
    0.60
    Simulation
    0.57
     sims
    0.56
    Activations Density 0.219%

    No Known Activations