© 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-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 8489
    Prev
    Next
    INDEX
    Explanations

    instances of the word "late" as well as expressions indicating brilliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 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
     Normdatei
    -0.69
     Bourgoin
    -0.62
    SerializedSize
    -0.62
     BoxFit
    -0.60
     MainAxisSize
    -0.57
     typelib
    -0.57
    OptionsMenu
    -0.57
    jamientos
    -0.57
    GOTREF
    -0.56
     Sociales
    -0.55
    POSITIVE LOGITS
     brilliant
    0.94
     lovely
    0.87
     amazing
    0.83
    amazing
    0.82
     beautiful
    0.82
    brilliant
    0.81
     gorgeous
    0.80
     Amazing
    0.79
     stunning
    0.78
     Brilliant
    0.77
    Activations Density 0.118%

    No Known Activations