© 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. 7078
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships or family structures

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

    "family" or families

    np_acts-logits-general · gemini-2.0-flash

    family or families

    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
     HasFactory
    -0.49
    ViewImports
    -0.48
    ガー
    -0.47
    SpringBootTest
    -0.46
    jsonwebtoken
    -0.45
    ChildScrollView
    -0.44
     sprintf
    -0.44
    XmlAccessType
    -0.43
    ihnachts
    -0.43
     encontram
    -0.43
    POSITIVE LOGITS
     family
    2.23
     families
    2.16
    family
    1.92
     Families
    1.86
     FAMILY
    1.82
    Family
    1.81
     Family
    1.81
    Families
    1.81
     famille
    1.77
    families
    1.75
    Activations Density 0.257%

    No Known Activations