© 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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 11930
    Prev
    Next
    INDEX
    Explanations

    references to specific chapters and their summaries in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ost
    -0.67
    öt
    -0.67
     ose
    -0.66
    consulté
    -0.65
    ot
    -0.62
    os
    -0.62
     Pire
    -0.61
    ánt
    -0.58
    eri
    -0.58
     Zool
    -0.58
    POSITIVE LOGITS
     chapters
    1.73
     chapter
    1.67
    chapters
    1.61
     Chapters
    1.58
     Chapter
    1.54
    CHAPTER
    1.54
     CHAPTER
    1.54
    Chapter
    1.47
    chapter
    1.47
    Chapters
    1.43
    Activations Density 0.057%

    No Known Activations