© 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. 10-GEMMASCOPE-RES-16K
    11. 5381
    Prev
    Next
    INDEX
    Explanations

    phrases expressing persistence or continuity despite challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.93
     propOrder
    -0.86
    ſelves
    -0.79
     المعيارى
    -0.78
    ArgsConstructor
    -0.74
    zzleHttp
    -0.72
    AddTagHelper
    -0.71
     Efq
    -0.70
     Theſe
    -0.69
    findpost
    -0.67
    POSITIVE LOGITS
     still
    1.02
    Still
    0.94
     Still
    0.93
    still
    0.90
     trotzdem
    0.80
     nonetheless
    0.79
     Trotzdem
    0.76
     Nonetheless
    0.76
     toch
    0.75
     Nevertheless
    0.75
    Activations Density 0.232%

    No Known Activations