© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 10390
    Prev
    Next
    INDEX
    Explanations

    references to individuals, specifically the name "Jones"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.68
    ⟬
    -0.68
    PerformLayout
    -0.63
     resourceCulture
    -0.62
    neſs
    -0.60
     endfor
    -0.59
    parsedMessage
    -0.58
     TextAppearance
    -0.57
     greateſt
    -0.57
     iſt
    -0.57
    POSITIVE LOGITS
    tex
    0.65
    ق
    0.51
    job
    0.49
    ions
    0.49
    TeX
    0.48
    TEX
    0.48
    mat
    0.48
    legend
    0.47
    ifdef
    0.46
     fairy
    0.45
    Activations Density 0.263%

    No Known Activations