© 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. 3522
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "Empire."

    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
     Infór
    -0.85
     Geſch
    -0.82
     témoig
    -0.81
    ஡
    -0.80
    ஦
    -0.80
    <unused23>
    -0.79
    parsedMessage
    -0.79
     Weiſe
    -0.79
    <unused42>
    -0.79
    <unused16>
    -0.79
    POSITIVE LOGITS
     New
    0.66
     NY
    0.55
     Empire
    0.50
    New
    0.46
    Empire
    0.42
     empire
    0.41
     NJ
    0.38
    NY
    0.38
     NYS
    0.35
     NYC
    0.34
    Activations Density 0.257%

    No Known Activations