© 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. 7572
    Prev
    Next
    INDEX
    Explanations

    words related to inclusion and including in context, particularly in programming and regulatory frameworks

    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
    HostException
    -0.56
    醐
    -0.47
    writerow
    -0.45
     FontWeight
    -0.44
    tingu
    -0.43
    lhes
    -0.43
     ioutil
    -0.42
     smtplib
    -0.41
    ifflin
    -0.41
    ecraft
    -0.41
    POSITIVE LOGITS
    jší
    0.50
     negó
    0.49
     didalam
    0.48
     considération
    0.47
     sorprender
    0.47
     consideration
    0.46
     dalamnya
    0.44
    Considerations
    0.44
    anskje
    0.43
     considerations
    0.43
    Activations Density 0.209%

    No Known Activations