© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 11782
    Prev
    Next
    INDEX
    Explanations

    terms related to economic supply and demand dynamics

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

    excess supply and availability

    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
    simpleType
    -0.41
    straw
    -0.40
    ọn
    -0.39
     dusting
    -0.39
     买
    -0.39
    SimpleName
    -0.38
     ModelExpression
    -0.38
     Malone
    -0.38
    awtextra
    -0.38
    __.__
    -0.37
    POSITIVE LOGITS
     surpluses
    0.45
     HFILL
    0.45
     MainAxisSize
    0.43
     totalSupply
    0.42
     مواليد
    0.42
    principalTable
    0.41
    taires
    0.41
     flooded
    0.40
     overwhelming
    0.39
    menistan
    0.39
    Activations Density 0.013%

    No Known Activations