Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10987
    Prev
    Next
    INDEX
    Explanations

    elements of programming structure, specifically related to JSON operations and asynchronous handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Asynchronous JavaScript promises

    np_acts-logits-general · gemini-2.0-flash

    asynchronous promise handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.78
     defaultstate
    -0.76
    RTEE
    -0.71
     ujednoznacz
    -0.66
    AnchorStyles
    -0.65
    IUrlHelper
    -0.65
     EconPapers
    -0.63
    Cyfarwyddwr
    -0.63
    writeFieldEnd
    -0.63
     esternos
    -0.62
    POSITIVE LOGITS
    async
    0.38
    回
    0.36
     send
    0.34
     promise
    0.34
     immediately
    0.33
    тится
    0.32
     reach
    0.32
    тился
    0.31
     sends
    0.31
     wait
    0.31
    Activations Density 0.252%

    No Known Activations