© 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
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5124
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verb "do" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     forKey
    -0.54
     Schwartz
    -0.53
    存于互联网档案馆
    -0.52
    RegressionTest
    -0.51
    脚注の使い方
    -0.51
     LRT
    -0.50
     AFB
    -0.48
     <<<<<<<<<<<<<<
    -0.47
     IMF
    -0.47
     SVP
    -0.46
    POSITIVE LOGITS
     does
    1.03
    does
    0.96
     did
    0.93
     do
    0.89
     Does
    0.88
    did
    0.87
    Does
    0.85
    Did
    0.77
     Did
    0.76
     DOES
    0.75
    Activations Density 0.214%

    No Known Activations