© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 101149
    Prev
    Next
    INDEX
    Explanations

    references to medical procedures and their effects

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

    Words or phrases indicating a pause, waiting, or transitional moment in an action or narrative - including terms like "reflect", "moment", "breath", "time to recharge", "hesitation", "pause", "long", "think", "after some time", and "silence" - often appearing in sequences describing a character's actions or system processes that involve brief delays.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    minecraftforge
    -0.42
    TagHelper
    -0.41
    OGND
    -0.40
     kec
    -0.35
    :✨
    -0.34
    CUSSION
    -0.34
     Ren
    -0.34
     Nest
    -0.33
    dür
    -0.33
     vik
    -0.33
    POSITIVE LOGITS
    səhifə
    0.56
    CloseOperation
    0.54
    RefNanny
    0.52
     demografica
    0.47
    WithIOException
    0.47
    IVEREF
    0.46
     المعيارى
    0.46
    ArgumentParser
    0.46
    PreExecute
    0.45
    AxisAlignment
    0.45
    Activations Density 0.050%

    No Known Activations