© 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. 14-GEMMASCOPE-RES-16K
    6. 8230
    Prev
    Next
    INDEX
    Explanations

    references to the act of settling or resolution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.83
     Hines
    -0.73
     McCormack
    -0.68
    ardians
    -0.65
     dessus
    -0.64
    ->__
    -0.62
     Gorman
    -0.61
     Rib
    -0.60
     pulsante
    -0.60
     Lass
    -0.60
    POSITIVE LOGITS
     Settle
    1.32
     settled
    1.30
     settle
    1.29
     settling
    1.25
    settle
    1.24
     SETTLE
    1.23
     settles
    1.18
    Settle
    1.14
     settlements
    1.13
    tling
    1.09
    Activations Density 0.251%

    No Known Activations