© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4795
    Prev
    Next
    INDEX
    Explanations

    the word "simply" and variations of it to indicate simplicity or straightforwardness in explanation

    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
    ISupport
    -1.00
     culturelles
    -0.84
     regardant
    -0.84
     colorés
    -0.84
     Gallardo
    -0.83
     debout
    -0.82
     passim
    -0.82
    timbangkan
    -0.82
     atteinte
    -0.81
     préfé
    -0.81
    POSITIVE LOGITS
     SIMPLE
    0.97
    simpleType
    0.96
     Simply
    0.92
    Simply
    0.92
     simply
    0.86
     Simple
    0.86
    PLY
    0.85
     simple
    0.84
    simply
    0.80
    er
    0.77
    Activations Density 0.095%

    No Known Activations