© 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 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. 20-GEMMASCOPE-RES-131K
    11. 67413
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to accountability in governance and social responsibility

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

    accountable for

    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
    idea
    -0.46
    styleType
    -0.42
    Erstellt
    -0.42
     idea
    -0.37
     viewWillAppear
    -0.36
    こんにちは
    -0.35
    ymce
    -0.35
    lectricité
    -0.34
     Weiden
    -0.34
    cass
    -0.33
    POSITIVE LOGITS
     accountability
    1.15
     Accountability
    1.02
     accountable
    0.89
     responsibility
    0.86
    responsibility
    0.73
    Responsibility
    0.73
     Verantwortung
    0.73
    tagHelperRunner
    0.72
     Responsibility
    0.71
     responsabilidad
    0.67
    Activations Density 0.006%

    No Known Activations