© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4672
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical specifications and programming concepts

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

    after roman numerals or math symbols

    np_acts-logits-general · gemini-2.0-flash

    chapter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -0.55
     Amongst
    -0.42
     firstly
    -0.40
    Mensagem
    -0.39
     Firstly
    -0.38
     amongst
    -0.38
     Parteien
    -0.37
     Confira
    -0.37
     amizade
    -0.37
     pihaknya
    -0.37
    POSITIVE LOGITS
     chapter
    0.76
    chapter
    0.72
     Chapter
    0.69
    Chapter
    0.68
    Capítulo
    0.65
    CHAPTER
    0.64
     CHAPTER
    0.60
     chapters
    0.55
     Chapters
    0.55
    tagHelperRunner
    0.54
    Activations Density 0.906%

    No Known Activations