© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 318
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and lineage

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

    a family's children

    np_acts-logits-general · gemini-2.0-flash

    birth order of children

    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
     Granny
    -0.51
     Uncle
    -0.49
     Grandpa
    -0.49
     Grandmother
    -0.46
     uncle
    -0.45
    évaluateur
    -0.45
    timm
    -0.45
    гран
    -0.44
    read
    -0.44
    Interim
    -0.44
    POSITIVE LOGITS
     eldest
    1.06
     youngest
    0.96
     oldest
    0.86
     son
    0.81
    oldest
    0.81
     figlio
    0.78
     sons
    0.74
     child
    0.72
     figli
    0.71
     pangan
    0.69
    Activations Density 0.181%

    No Known Activations