© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4521
    Prev
    Next
    INDEX
    Explanations

    mentions of artificial intelligence and its implications

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

    "AI" or "Siri."

    np_acts-logits-general · gemini-2.0-flash

    AI improvement Siri

    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
    CloseOperation
    -0.69
     upraw
    -0.44
     للمعارف
    -0.43
     EconPapers
    -0.43
    IBarButtonItem
    -0.41
    出版年
    -0.39
    KommentareTeilen
    -0.39
     يتيمه
    -0.38
    Tikang
    -0.38
     erschienen
    -0.38
    POSITIVE LOGITS
     robot
    1.17
     AI
    1.14
     robots
    1.07
     robotic
    1.02
    AI
    0.96
    robot
    0.96
     automated
    0.93
     automation
    0.93
     Robot
    0.88
     robotics
    0.88
    Activations Density 0.403%

    No Known Activations