© 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. 14888
    Prev
    Next
    INDEX
    Explanations

    references to family lineage and ancestral connections

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

    Possessive pronouns followed by family members

    np_acts-logits-general · gemini-2.0-flash

    family members and ancestry

    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
    WriteAttribute
    -0.72
    \{\\
    -0.70
     мәкал
    -0.67
    RegressionTest
    -0.67
    Portail
    -0.61
     NSCoder
    -0.60
    msgTypes
    -0.60
    TestingModule
    -0.59
    TagMode
    -0.59
     transfieras
    -0.58
    POSITIVE LOGITS
     grandfather
    1.86
     ancestors
    1.83
     grandparents
    1.78
     ancestor
    1.68
     grandmother
    1.67
    grandfather
    1.61
     Grandfather
    1.58
     grandpa
    1.53
     forefathers
    1.50
     Grandmother
    1.45
    Activations Density 0.199%

    No Known Activations