© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 41978
    Prev
    Next
    INDEX
    Explanations

    phrases related to reading aloud

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

    read aloud

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     asiático
    -0.35
     asiática
    -0.34
     mukana
    -0.34
     extranjera
    -0.30
     asiatique
    -0.29
     sanitarias
    -0.29
     aient
    -0.28
     afectada
    -0.27
     afectados
    -0.27
     gevolg
    -0.26
    POSITIVE LOGITS
     aloud
    1.67
    loud
    1.05
     loud
    0.99
    Loud
    0.96
     Loud
    0.90
     loudly
    0.89
     openly
    0.77
     głoś
    0.77
    大声
    0.75
    MLLoader
    0.73
    Activations Density 0.008%

    No Known Activations