© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 28625
    Prev
    Next
    INDEX
    Explanations

    references to caregiving and community support for aging individuals

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

    fellowship and community

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hout
    -0.40
    rodek
    -0.38
     conduire
    -0.38
     length
    -0.38
    καν
    -0.38
    Tarea
    -0.37
    VIAF
    -0.37
    嬢
    -0.37
    epam
    -0.37
    NavItem
    -0.36
    POSITIVE LOGITS
    fellow
    0.91
     fellowship
    0.89
     camaraderie
    0.88
     sesama
    0.84
     fellow
    0.81
    __((
    0.81
     getGroup
    0.80
     grouping
    0.80
     FELLOW
    0.79
    Fellow
    0.78
    Activations Density 0.235%

    No Known Activations