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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 1035
    Prev
    Next
    INDEX
    Explanations

    references to PDF documents and files

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ծանոթ
    -0.60
    trunk
    -0.55
    Unmarshal
    -0.51
    ="'+
    -0.50
     plat
    -0.50
    NamedQueries
    -0.49
    lassung
    -0.48
    нтен
    -0.48
     Caroline
    -0.47
    ^=
    -0.47
    POSITIVE LOGITS
    pdf
    3.68
    PDF
    3.12
     pdf
    3.10
     PDF
    2.98
     PDFs
    2.56
    Pdf
    2.35
     Pdf
    2.25
    docx
    1.62
     docx
    1.20
     Acrobat
    1.12
    Activations Density 0.086%

    No Known Activations