© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 28414
    Prev
    Next
    INDEX
    Explanations

    phrases related to phasing out or transitioning from one state to another

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

    phasing out gradually

    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
    setContentType
    -0.35
     cure
    -0.33
    entuh
    -0.30
     Nutt
    -0.28
     doom
    -0.28
     po
    -0.28
     aluguel
    -0.28
     NSCoder
    -0.28
    
    -0.28
     Cure
    -0.27
    POSITIVE LOGITS
     phased
    0.86
     phasing
    0.85
     gradualmente
    0.68
     jspb
    0.66
     Gradually
    0.66
     gradually
    0.66
    逐步
    0.62
    WaitGroup
    0.62
    Gradu
    0.61
     disambiguazione
    0.61
    Activations Density 0.026%

    No Known Activations