© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 16361
    Prev
    Next
    INDEX
    Explanations

    phonetically pronounced words and linguistic elements

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

    referring to pronunciation or phonetics

    np_acts-logits-general · gemini-2.0-flash

    pronunciation and stress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    SequentialGroup
    -0.68
    enderror
    -0.63
     purpoſe
    -0.59
    
    -0.57
    UnitTesting
    -0.57
     InputDecoration
    -0.57
     fubject
    -0.57
    rungsseite
    -0.56
    存于互联网档案馆
    -0.56
    RemoveField
    -0.56
    POSITIVE LOGITS
     pronouncing
    0.42
     pronunci
    0.38
    Pronunciation
    0.35
    Pron
    0.35
     pronounced
    0.34
     pronounce
    0.34
     pronunciation
    0.34
     Pron
    0.34
    pronounced
    0.34
     acento
    0.33
    Activations Density 0.126%

    No Known Activations