© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 29802
    Prev
    Next
    INDEX
    Explanations

    temporal and age-related references in the context of health and developmental milestones

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

    early stages of life or time

    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
    τογραφ
    -0.66
     ivelany
    -0.64
     CreateTagHelper
    -0.64
    يكب
    -0.60
     Signalez
    -0.58
    webElementXpaths
    -0.56
    ScopeManager
    -0.56
    Geplaatst
    -0.56
     nahilalakip
    -0.54
    новниш
    -0.54
    POSITIVE LOGITS
     makeStyles
    0.62
    unconfirmed
    0.55
     EconPapers
    0.54
    matchCondition
    0.54
    INSEE
    0.52
    ModelForm
    0.51
    RetentionPolicy
    0.50
    slightly
    0.49
     temprana
    0.49
     internetowa
    0.49
    Activations Density 0.152%

    No Known Activations