© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 100468
    Prev
    Next
    INDEX
    Explanations

    terms and phrases associated with predictive modeling and statistical analysis related to neural networks

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

    the neuron detects salient content words—domain-specific nouns and technical keywords (important topic words) rather than function words.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    AnimationsModule
    -0.48
    ttemberg
    -0.47
     Photocase
    -0.47
    icksburg
    -0.46
    Scalars
    -0.45
    AutoresizingMask
    -0.45
    ፩
    -0.45
     ligiloj
    -0.45
    ↻
    -0.45
    はじめに
    -0.44
    POSITIVE LOGITS
     <=",
    0.42
     Chwiliwch
    0.35
    JNIEnv
    0.35
     ويكيپيديا
    0.34
     Heaven
    0.33
    ྣ
    0.33
     Italijani
    0.33
    utilisons
    0.32
     चीज़ों
    0.32
     weak
    0.31
    Activations Density 0.359%

    No Known Activations