© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 371
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases related to specialized fields, including finance, medicine, and engineering

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

    before applications, formula, implant, therapy, or Bluetooth

    np_acts-logits-general · gemini-2.0-flash

    medical and technical applications

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     ligiloj
    -0.61
    FormTagHelper
    -0.59
    DockStyle
    -0.55
    CloseOperation
    -0.52
    SharedDtor
    -0.50
     propOrder
    -0.49
    MetaObject
    -0.48
    RegistryLite
    -0.47
     Mandate
    -0.47
    complexType
    -0.46
    POSITIVE LOGITS
    saraba
    0.43
     فريبيس
    0.42
     industry
    0.35
    mobileqq
    0.34
     싶
    0.34
    SqlClient
    0.33
    nehmen
    0.33
     use
    0.32
    싶
    0.31
     UnityEditor
    0.31
    Activations Density 1.054%

    No Known Activations