© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 4203
    Prev
    Next
    INDEX
    Explanations

    references to family and its importance in various contexts

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

    "family" and related contexts

    np_acts-logits-general · gemini-2.0-flash

    family planning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tarts
    -0.66
     Sorbonne
    -0.65
     Manifesto
    -0.64
     Obispo
    -0.64
     Retard
    -0.63
     Keats
    -0.63
    وذ
    -0.63
     uç
    -0.62
     Ahi
    -0.62
     Conqueror
    -0.62
    POSITIVE LOGITS
     family
    1.23
     Family
    1.09
    family
    1.07
    Family
    1.01
     FAMILY
    0.98
     families
    0.97
    FAMILY
    0.96
     Families
    0.89
    Families
    0.88
    families
    0.87
    Activations Density 0.068%

    No Known Activations