© 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. 0-GEMMASCOPE-RES-16K
    11. 7917
    Prev
    Next
    INDEX
    Explanations

    instances of the word "realize" and its variations, indicating a focus on moments of understanding or awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DataSnapshot
    -0.45
    RTEX
    -0.45
     campe
    -0.44
    ó
    -0.44
     conventional
    -0.44
     Cro
    -0.42
    Халык
    -0.40
    بوابة
    -0.40
    JAKARTA
    -0.40
     Eisen
    -0.39
    POSITIVE LOGITS
     realize
    0.64
     realizing
    0.62
     realise
    0.62
     realizes
    0.57
     realising
    0.56
     integrates
    0.55
    WebVitals
    0.55
     realises
    0.54
     integrate
    0.54
     realización
    0.52
    Activations Density 0.234%

    No Known Activations