© 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. 19-GEMMASCOPE-RES-16K
    11. 2732
    Prev
    Next
    INDEX
    Explanations

    phrases related to academic centers and their specific areas of research or study

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    -0.53
     spē
    -0.50
    клу
    -0.48
    BeginContext
    -0.46
     dolu
    -0.46
     :
    -0.44
     part
    -0.43
    1
    -0.43
     te
    -0.43
    te
    -0.43
    POSITIVE LOGITS
     Мексичка
    1.16
     دیکھیے
    0.78
     Efq
    0.78
    ✨:
    0.78
    sizeCache
    0.77
    ImageContext
    0.77
    UserScript
    0.77
    InfoWindow
    0.75
     Conſ
    0.74
    makeConstraints
    0.73
    Activations Density 0.117%

    No Known Activations