© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 13404
    Prev
    Next
    INDEX
    Explanations

    references to subsystems and subcategories within a technical or structured context

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    The token "sub" followed by another token

    np_acts-logits-general · gemini-2.0-flash

    sub prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     ligiloj
    -0.51
     democrática
    -0.44
    orianCalendar
    -0.44
     ThemeData
    -0.42
     isempty
    -0.40
     kinases
    -0.39
     calendriers
    -0.39
    strtotime
    -0.39
    Odour
    -0.39
    EXPERIENCE
    -0.38
    POSITIVE LOGITS
     sub
    2.36
     Sub
    2.28
    Sub
    2.16
    sub
    2.06
     SUB
    1.98
    SUB
    1.87
     getSub
    1.78
    getSub
    1.70
     subs
    1.64
    サブ
    1.55
    Activations Density 0.189%

    No Known Activations