© 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
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 11395
    Prev
    Next
    INDEX
    Explanations

    scientific terminology and research-related phrases, especially those related to treatments and medical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    期刊论文
    -0.48
    ьаж
    -0.47
    Method
    -0.47
    Thing
    -0.47
    Issue
    -0.47
    thing
    -0.46
    AnchorTagHelper
    -0.46
    Portion
    -0.45
    Area
    -0.45
    Series
    -0.44
    POSITIVE LOGITS
    Personendaten
    0.52
     Wikiseite
    0.48
     wikipagina
    0.42
     cultuur
    0.42
    withIdentifier
    0.40
     bedrag
    0.40
     actualidad
    0.40
    extrême
    0.40
    CloseOperation
    0.39
     partij
    0.39
    Activations Density 2.226%

    No Known Activations