© 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. 11-GEMMASCOPE-RES-16K
    6. 9141
    Prev
    Next
    INDEX
    Explanations

    geographic location identifiers or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/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.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comunicaciones
    -0.48
     esimer
    -0.47
     sanitarias
    -0.47
     huom
    -0.45
     Infórmanos
    -0.44
    chsel
    -0.44
     perfecta
    -0.43
    holdet
    -0.43
     garantías
    -0.43
     Ursache
    -0.42
    POSITIVE LOGITS
     IBOutlet
    0.57
    parsedMessage
    0.49
    posedge
    0.48
     ObjectParameter
    0.46
     South
    0.45
    addCriterion
    0.44
    QtCore
    0.43
     W
    0.43
     N
    0.43
    SPONSORED
    0.41
    Activations Density 0.274%

    No Known Activations