© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 112283
    Prev
    Next
    INDEX
    Explanations

    phrases related to load management and handling in mechanical systems

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

    load and workload contexts

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    httphttps
    -0.70
     Paglinawan
    -0.59
    Enllaces
    -0.58
    -------------</
    -0.58
    istoitu
    -0.57
     CreateTagHelper
    -0.56
    windowFixed
    -0.53
     يتيمه
    -0.53
     Administrativna
    -0.53
     manhã
    -0.52
    POSITIVE LOGITS
     Load
    0.80
     load
    0.78
    Load
    0.73
    load
    0.72
     нагрузки
    0.61
    Workload
    0.60
     нагруз
    0.58
     LOAD
    0.58
    LOAD
    0.57
     beban
    0.54
    Activations Density 0.012%

    No Known Activations