© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8450
    Prev
    Next
    INDEX
    Explanations

    keywords related to the development and implications of artificial intelligence and autonomous technologies

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

    Artificial intelligence and robots

    np_acts-logits-general · gemini-2.0-flash

    AI, robots, voice assistants

    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
    atguigu
    -0.66
    ferrer
    -0.61
    swick
    -0.57
     Paglinawan
    -0.57
     Thule
    -0.55
     Whigs
    -0.55
    busch
    -0.55
     Legendre
    -0.52
     Morm
    -0.51
    blende
    -0.51
    POSITIVE LOGITS
     robot
    1.79
     AI
    1.79
     robots
    1.68
     Artificial
    1.65
     artificial
    1.59
     robotic
    1.57
    Artificial
    1.49
     automated
    1.46
    robot
    1.45
     Robot
    1.44
    Activations Density 0.334%

    No Known Activations