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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 112047
    Prev
    Next
    INDEX
    Explanations

    terms and phrases associated with closed systems and closed structures

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

    closed state or system

    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
    effectiveness
    -0.41
    effort
    -0.41
     Aspekte
    -0.39
     the
    -0.39
    trino
    -0.38
     Phần
    -0.38
    mstyle
    -0.38
    effetto
    -0.37
    abilities
    -0.36
     Effekt
    -0.36
    POSITIVE LOGITS
    Closed
    1.14
     Closed
    1.14
     closed
    1.10
    closed
    1.02
     CLOSED
    1.00
    CLOSED
    0.94
    isClosed
    0.92
     tertutup
    0.91
     Enclosed
    0.83
     fermé
    0.81
    Activations Density 0.009%

    No Known Activations