© 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 - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 14523
    Prev
    Next
    INDEX
    Explanations

    references to family relationships and connections

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

    Family members (dad, father, husband, mom, etc.)

    np_acts-logits-general · gemini-2.0-flash

    parents and spouses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.98
     kasarigan
    -0.90
    UnsafeEnabled
    -0.87
    itself
    -0.84
     themſelves
    -0.82
    évaluateur
    -0.79
     Itself
    -0.77
     itself
    -0.76
    ագրություններ
    -0.74
     autorytatywna
    -0.74
    POSITIVE LOGITS
     who
    0.71
    ’
    0.67
    '
    0.61
    ,
    0.59
     décédé
    0.47
    atial
    0.47
    Välislingid
    0.46
     детства
    0.45
     whom
    0.45
    
    0.43
    Activations Density 0.175%

    No Known Activations