© 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. 18-GEMMASCOPE-RES-16K
    11. 10410
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and connections, particularly involving neighbors and cousins

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

    about relatives or close entities

    np_acts-logits-general · gemini-2.0-flash

    family and close relations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lccn
    -0.71
    LEncoder
    -0.68
    ressible
    -0.64
    intios
    -0.62
     EdgeInsets
    -0.61
    expandindo
    -0.58
     ]
    -0.57
    phosa
    -0.57
    TagMode
    -0.57
    "){
    -0.56
    POSITIVE LOGITS
     immédi
    0.85
     directos
    0.76
     suyo
    0.64
     cercanos
    0.61
    们的
    0.60
    們
    0.58
     terdekat
    0.58
     whom
    0.58
    们
    0.56
     commerciaux
    0.54
    Activations Density 0.355%

    No Known Activations