© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 39116
    Prev
    Next
    INDEX
    Explanations

    the concept of insufficiency or being just enough

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

    barely + minimal state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.51
     kasarigan
    -0.50
    存于互联网档案馆
    -0.47
     AttributeSet
    -0.47
    pyplot
    -0.47
    :^(
    -0.45
     Wisata
    -0.44
    醐
    -0.44
     this
    -0.44
     Sequo
    -0.44
    POSITIVE LOGITS
     barely
    1.97
     scarcely
    1.21
     hardly
    1.13
     Hardly
    1.09
     Bare
    0.88
    bare
    0.85
    Bare
    0.84
     едва
    0.80
     barley
    0.75
     nearly
    0.71
    Activations Density 0.002%

    No Known Activations