© 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. 27-GEMMASCOPE-RES-16K
    11. 8817
    Prev
    Next
    INDEX
    Explanations

    phrases related to greetings or initial conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XtraReports
    -0.67
    localctx
    -0.59
    contentLoaded
    -0.58
    WindowConstants
    -0.53
    utilisons
    -0.53
     karş
    -0.49
    各样的
    -0.48
     Pritchard
    -0.47
     prêtres
    -0.47
    المناصب
    -0.45
    POSITIVE LOGITS
    ey
    0.82
     Toy
    0.73
    Toy
    0.69
    yy
    0.67
    oy
    0.65
     toy
    0.64
    Vay
    0.63
    loy
    0.62
    ay
    0.61
     Vay
    0.61
    Activations Density 0.423%

    No Known Activations