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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1155
    Prev
    Next
    INDEX
    Explanations

    terms related to computational processes and related technologies

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

    instances of the term "computed" as it relates to programming or coding concepts

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

    compute and computed terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    BufferException
    -1.14
    httphttps
    -0.86
     NSCoder
    -0.85
    windowFixed
    -0.82
    MemoryWarning
    -0.82
     /\.(
    -0.78
    إنه
    -0.78
     فريبيس
    -0.77
    RTLE
    -0.72
    WebVitals
    -0.71
    POSITIVE LOGITS
     tomography
    0.66
     engine
    0.58
    engine
    0.53
    computed
    0.52
    a
    0.49
     columna
    0.49
    ียว
    0.48
     Engine
    0.47
     Comput
    0.47
    utto
    0.46
    Activations Density 0.028%

    No Known Activations