© 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 - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 11956
    Prev
    Next
    INDEX
    Explanations

    references to specific compounds or reagents often used in scientific research

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

    This neuron identifies author names in academic citations, particularly focusing on surnames like "Truran" or "Trizol" that appear before commas or identifiers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    author names in academic citations, particularly the surname "Truran".

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.65
     externi
    -0.57
    AndEndTag
    -0.50
    ური
    -0.49
     FetchType
    -0.48
    RegistryLite
    -0.48
    脚注の使い方
    -0.48
    
    -0.47
     häm
    -0.47
    MenuInflater
    -0.45
    POSITIVE LOGITS
     Tr
    0.73
    Tr
    0.68
     TR
    0.62
     tr
    0.62
     TRX
    0.56
     Tru
    0.54
     trx
    0.53
    tr
    0.50
    TR
    0.48
     Trp
    0.46
    Activations Density 0.730%

    No Known Activations