© 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. 805
    Prev
    Next
    INDEX
    Explanations

    terms related to preparation and timing in medical contexts

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

    a before or after relationship

    np_acts-logits-general · gemini-2.0-flash

    before, during, after

    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
     utafitiHapana
    -0.64
    MemoryWarning
    -0.59
     Infórmanos
    -0.58
    IsMutable
    -0.57
    TintMode
    -0.56
    AndView
    -0.56
     autorytatywna
    -0.55
    contentLoaded
    -0.53
    MessageTagHelper
    -0.52
    httphttps
    -0.49
    POSITIVE LOGITS
     preparation
    0.84
     pre
    0.82
     before
    0.82
     beforehand
    0.81
     anticipation
    0.77
     preparatory
    0.76
    before
    0.73
     preseason
    0.73
    事前
    0.72
     antes
    0.72
    Activations Density 0.539%

    No Known Activations