© 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 EvalsExportsinterp-engineNEWAPI 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. 17799
    Prev
    Next
    INDEX
    Explanations

    concepts related to future advancements in healthcare and genetics

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

    future treatments and scientific determination

    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
     suele
    -0.52
     ajudá
    -0.51
     brukar
    -0.51
     suelen
    -0.50
     usually
    -0.47
    findpost
    -0.45
     often
    -0.45
     Usually
    -0.44
     meistens
    -0.42
    typeorm
    -0.42
    POSITIVE LOGITS
     künftig
    1.12
     someday
    1.04
     future
    1.02
    future
    1.01
     zukünf
    0.92
     künf
    0.90
     futuro
    0.90
     будущего
    0.88
    Future
    0.84
     futura
    0.84
    Activations Density 0.169%

    No Known Activations