© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1586
    Prev
    Next
    INDEX
    Explanations

    terms related to real-time data processing and streaming technologies

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

    live or current events

    np_acts-logits-general · gemini-2.0-flash

    real-time data and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfieras
    -0.66
     "..\..\
    -0.62
     transférez
    -0.61
    ItemBackground
    -0.60
     defaultstate
    -0.59
     "..\..\..\
    -0.57
    AnchorTagHelper
    -0.52
    tvguidetime
    -0.51
    WithIOException
    -0.50
    艋
    -0.49
    POSITIVE LOGITS
     instantaneous
    0.64
     immedi
    0.64
    immediate
    0.61
     live
    0.58
    instant
    0.58
    live
    0.57
     instant
    0.56
     Live
    0.55
     immediate
    0.55
    Live
    0.53
    Activations Density 0.603%

    No Known Activations