© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73797
    Prev
    Next
    INDEX
    Explanations

    technical terms and mechanisms related to engineering systems, particularly in control and feedback processes

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

    feedback control mechanisms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    TemporalType
    -0.36
     lucky
    -0.36
     dem
    -0.35
     trick
    -0.33
    DisplayName
    -0.32
     Outsider
    -0.32
    otros
    -0.32
    vors
    -0.32
    weisen
    -0.32
     abger
    -0.31
    POSITIVE LOGITS
     WebDriverWait
    0.62
    TagMode
    0.55
    CloseOperation
    0.54
    HasForeignKey
    0.53
    сылкі
    0.52
     InputDecoration
    0.52
     Irán
    0.52
    DeleteBehavior
    0.50
    :✨
    0.48
    Tembelea
    0.47
    Activations Density 0.117%

    No Known Activations