© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 2607
    Prev
    Next
    INDEX
    Explanations

    instances of the word "notion" and variations of the term "return" within an analytical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tikang
    -0.67
    ConstraintMaker
    -0.65
     OMITBAD
    -0.61
    StoreMessageInfo
    -0.61
     تضيفلها
    -0.61
    IntoConstraints
    -0.60
    webElementXpaths
    -0.57
    تقاوى
    -0.57
    LookAnd
    -0.57
    UserScript
    -0.57
    POSITIVE LOGITS
     reference
    0.57
     notion
    0.48
     entry
    0.45
     linkage
    0.43
    서
    0.42
     notions
    0.39
    发生了
    0.39
     return
    0.38
     مورد
    0.35
    ENTRY
    0.34
    Activations Density 0.193%

    No Known Activations