© 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. 7-GEMMASCOPE-RES-16K
    11. 15195
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Introduction" and related terms that indicate the start of a document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    msgTypes
    -0.62
     }{@
    -0.54
     disambiguazione
    -0.54
    ImageContext
    -0.53
    MigrationBuilder
    -0.52
    expandindo
    -0.50
    WebElementEntity
    -0.50
    гиоз
    -0.48
     zijne
    -0.48
    ंदीखरीदारी
    -0.47
    POSITIVE LOGITS
    Introduction
    2.22
     Introduction
    2.20
     introduction
    2.17
    INTRODUCTION
    1.88
     INTRODUCTION
    1.87
    introduction
    1.86
    Intro
    1.74
     intro
    1.70
     Intro
    1.70
     introductions
    1.66
    Activations Density 0.216%

    No Known Activations