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

    Neuronpedia

    Jacobian LensNEW
    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. 12808
    Prev
    Next
    INDEX
    Explanations

    references to familial and parental relationships

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

    Family relationships (son, daughter, children)

    np_acts-logits-general · gemini-2.0-flash

    parent-child relationships

    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
    modelBuilder
    -0.57
    tagHelperRunner
    -0.48
     Fonction
    -0.46
     docente
    -0.46
    WriteBarrier
    -0.44
    hyung
    -0.44
     protoimpl
    -0.43
     Mestre
    -0.43
    gway
    -0.43
     sensei
    -0.43
    POSITIVE LOGITS
     son
    2.40
     daughter
    2.20
     grandson
    2.02
     sons
    1.96
     granddaughter
    1.89
    daughter
    1.82
     daughters
    1.82
     Son
    1.80
    Son
    1.75
     Daughter
    1.74
    Activations Density 0.172%

    No Known Activations