© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 30979
    Prev
    Next
    INDEX
    Explanations

    elements related to PDF file processing and manipulation

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

    convert pdf files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.63
    enumi
    -0.59
    oprecip
    -0.57
     Sputnik
    -0.57
     kulak
    -0.56
     setuptools
    -0.56
     cardiaque
    -0.55
    thalam
    -0.55
     broadcasting
    -0.54
    oprecipitation
    -0.54
    POSITIVE LOGITS
     PDF
    0.92
    pdf
    0.79
    PDF
    0.79
     pdf
    0.75
     document
    0.73
    Pdf
    0.72
     PDFs
    0.71
     Document
    0.70
     printer
    0.69
     paper
    0.68
    Activations Density 0.140%

    No Known Activations