Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 15796
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to robotics and motor control systems

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

    Code, equations, or related symbols

    np_acts-logits-general · gemini-2.0-flash

    robotics and control systems

    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
     ticket
    -0.57
    ticket
    -0.54
    rhosis
    -0.52
    ftagPool
    -0.51
     telefónica
    -0.50
    kheim
    -0.50
    falz
    -0.49
    fileSize
    -0.48
    Watermark
    -0.47
    carat
    -0.47
    POSITIVE LOGITS
     rospy
    0.81
     Robotics
    0.80
    wpi
    0.76
     robotics
    0.74
    Robotics
    0.73
     MonoBehaviour
    0.71
     Arduino
    0.70
     Robot
    0.69
     robot
    0.69
     sensors
    0.68
    Activations Density 0.309%

    No Known Activations