© 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. 3-GEMMASCOPE-RES-16K
    11. 8650
    Prev
    Next
    INDEX
    Explanations

    terms related to data storage and memory management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oa̍t
    -0.57
     CommonModule
    -0.54
     desglose
    -0.53
     Fleece
    -0.51
    entuh
    -0.50
     poética
    -0.49
     democrática
    -0.49
     democrá
    -0.48
     handker
    -0.48
     fleece
    -0.47
    POSITIVE LOGITS
     stored
    0.87
     Stored
    0.85
     storing
    0.85
     保存
    0.84
     Storing
    0.83
    btnSave
    0.82
    Storing
    0.81
    保存
    0.80
     saved
    0.80
     Save
    0.78
    Activations Density 0.462%

    No Known Activations