© 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-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 6812
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "settling" or reaching an agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gorman
    -0.74
     pulsante
    -0.73
    aniline
    -0.71
     Polri
    -0.69
     Hines
    -0.69
    portlet
    -0.68
    navigationBar
    -0.67
    żer
    -0.66
    łec
    -0.65
     gatto
    -0.64
    POSITIVE LOGITS
     settle
    2.07
     settled
    2.00
     settling
    2.00
     SETTLE
    1.94
     settles
    1.88
     Settle
    1.88
    settle
    1.85
     settlement
    1.71
     Settlement
    1.70
    Settle
    1.69
    Activations Density 0.066%

    No Known Activations