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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 42545
    Prev
    Next
    INDEX
    Explanations

    indicators of economic growth and improvement

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

    economic growth and prosperity

    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
    writeFieldEnd
    -0.51
     futuras
    -0.45
     }{@
    -0.44
     Nicolson
    -0.41
     Öffentlichkeit
    -0.41
     lightsaber
    -0.40
    ancers
    -0.40
    illères
    -0.40
    таратура
    -0.40
     Thacker
    -0.39
    POSITIVE LOGITS
     kasarigan
    0.46
    Vidite
    0.42
    AndroidJUnit
    0.42
     surge
    0.41
    sizeCache
    0.39
    增
    0.37
     spurt
    0.37
     rebound
    0.36
     vermo
    0.36
     estim
    0.36
    Activations Density 0.027%

    No Known Activations