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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12551
    Prev
    Next
    INDEX
    Explanations

    instances of the word "settle" and its variants, indicating a focus on discussions or resolutions related to arrangements or agreements

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

    settle in, settle for, settle into

    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
     UnityEngine
    -0.66
    Autowired
    -0.65
    Barcelona
    -0.61
    ⓧ
    -0.59
    iostream
    -0.59
    Pherson
    -0.58
     חיצוניים
    -0.58
     Brigade
    -0.57
     Prieto
    -0.57
    BarButtonItem
    -0.57
    POSITIVE LOGITS
     settle
    1.02
     SETTLE
    1.00
     Settle
    0.96
     settlement
    0.94
    settle
    0.91
    Settle
    0.90
     settled
    0.87
     Settlement
    0.85
     settles
    0.82
     settling
    0.81
    Activations Density 0.010%

    No Known Activations