© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 7465
    Prev
    Next
    INDEX
    Explanations

    references to scientific research methods and protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mergeFrom
    -0.52
    endphp
    -0.48
    ViewImports
    -0.48
     AssemblyProduct
    -0.48
    fromnode
    -0.47
    ).__
    -0.46
     دیکھیے
    -0.45
     تانيه
    -0.45
    writerow
    -0.45
     betweenstory
    -0.44
    POSITIVE LOGITS
     prevent
    1.52
     improves
    1.47
     prevents
    1.45
    prevent
    1.44
     helps
    1.41
     ensures
    1.41
     preventing
    1.41
     improve
    1.38
     ensure
    1.36
     improving
    1.30
    Activations Density 2.787%

    No Known Activations