© 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. 5-GEMMASCOPE-RES-16K
    6. 3294
    Prev
    Next
    INDEX
    Explanations

    asynchronous programming constructs like "await" and "async."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     structure
    -0.51
    OGND
    -0.49
    ca
    -0.47
    с
    -0.47
     '
    -0.46
    </i>
    -0.46
    struts
    -0.45
    ber
    -0.45
    док
    -0.45
    群
    -0.45
    POSITIVE LOGITS
     await
    2.48
    await
    2.37
     awaits
    1.76
    Await
    1.58
     awaiting
    1.52
     awaited
    1.38
     CreateTagHelper
    1.25
    waits
    1.20
     Waits
    1.16
     wait
    1.16
    Activations Density 0.028%

    No Known Activations