© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 9353
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "settings" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    csolódó
    -0.90
     isolada
    -0.87
     virtuales
    -0.87
     otomatig
    -0.83
     Virol
    -0.83
     hvem
    -0.81
     bosom
    -0.81
     AssemblyProduct
    -0.81
    writeField
    -0.81
    mbggenerated
    -0.80
    POSITIVE LOGITS
    Settings
    2.00
     settings
    1.97
     Settings
    1.91
    settings
    1.89
     SETTINGS
    1.53
    SETTINGS
    1.45
     setting
    1.38
     Setting
    1.30
    getSettings
    1.28
     SETTING
    1.28
    Activations Density 0.084%

    No Known Activations