© 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. 3-GEMMASCOPE-RES-16K
    6. 1961
    Prev
    Next
    INDEX
    Explanations

    references to PDF files and related formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Segoe
    -0.60
     MonoBehaviour
    -0.60
    coroutines
    -0.59
    createStatement
    -0.56
    сни
    -0.55
    Nomenclature
    -0.54
    зни
    -0.52
    ']==
    -0.52
    ///<
    -0.52
     plats
    -0.52
    POSITIVE LOGITS
     PDF
    2.91
    PDF
    2.90
    pdf
    2.83
     pdf
    2.76
     PDFs
    2.52
    Pdf
    2.26
     Pdf
    2.20
    docx
    1.22
     Acrobat
    1.14
     Ebook
    1.01
    Activations Density 0.114%

    No Known Activations