© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 646
    Prev
    Next
    INDEX
    Explanations

    initial commands or instructions related to programming

    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
     currently
    -0.81
     Currently
    -0.80
     actuellement
    -0.77
     aktuell
    -0.74
    currently
    -0.72
     Wikiseite
    -0.72
     derzeit
    -0.71
    tualmente
    -0.71
     atualmente
    -0.70
    Currently
    -0.70
    POSITIVE LOGITS
     soon
    0.75
     later
    0.71
    Soon
    0.68
     Soon
    0.61
    later
    0.60
     había
    0.57
     hoped
    0.56
    WithIOException
    0.56
     يتيمه
    0.56
     createStore
    0.55
    Activations Density 1.529%

    No Known Activations