© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 83413
    Prev
    Next
    INDEX
    Explanations

    aspects related to change and development in various contexts

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

    future events

    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
     Previous
    -0.56
     previous
    -0.55
    previous
    -0.52
    Previous
    -0.51
     PREVIOUS
    -0.50
     damal
    -0.47
     previa
    -0.47
    earlier
    -0.47
     précédent
    -0.45
    anterior
    -0.45
    POSITIVE LOGITS
     komende
    1.55
    今後
    1.38
    これから
    1.30
     prochaines
    1.29
     next
    1.28
    今後も
    1.25
     henceforth
    1.24
     hereafter
    1.22
     prossima
    1.20
     upcoming
    1.20
    Activations Density 0.129%

    No Known Activations