© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 12328
    Prev
    Next
    INDEX
    Explanations

    relations and connections between entities, particularly in comparative or evaluative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    both ... and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     semua
    -0.60
     wszystkich
    -0.59
     jopa
    -0.57
     všetkých
    -0.52
     allemaal
    -0.52
     всіх
    -0.51
     nejen
    -0.50
    ItemBackground
    -0.50
     tutte
    -0.49
     persino
    -0.48
    POSITIVE LOGITS
     respective
    0.70
     equally
    0.69
    各自
    0.67
     separately
    0.63
     одина
    0.61
     Equally
    0.60
     igualmente
    0.59
     alike
    0.57
     respectively
    0.55
     gleicher
    0.55
    Activations Density 0.105%

    No Known Activations