© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104239
    Prev
    Next
    INDEX
    Explanations

    instances of technical terms and processes related to circuit design and functionality

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

    End-of-sentence or end-of-section punctuation marks in technical documents, often followed by citation references, figure captions, or new content sections.

    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
    richTextPanel
    -0.62
     propOrder
    -0.55
    :✨
    -0.47
     BrowserModule
    -0.42
    はじめに
    -0.41
    nologue
    -0.40
    TagMode
    -0.40
     Ubic
    -0.39
     autorytatywna
    -0.39
    peł
    -0.39
    POSITIVE LOGITS
     الحره
    0.43
     nakalista
    0.42
    enumii
    0.42
     Biôgrafia
    0.41
    ⅘
    0.41
    发表于
    0.40
    RegressionTest
    0.40
    EndContext
    0.38
     Administrativna
    0.38
    Applies
    0.36
    Activations Density 0.204%

    No Known Activations