© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 20932
    Prev
    Next
    INDEX
    Explanations

    references to family relationships and caregiving roles

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

    elderly family members and their relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.41
     gynhyrchwyd
    -0.37
     otomatig
    -0.32
     leid
    -0.31
    tserrat
    -0.30
    生
    -0.29
    Dez
    -0.29
    <?
    -0.29
    experimental
    -0.28
    育
    -0.28
    POSITIVE LOGITS
     elderly
    0.98
    👵
    0.96
     Elderly
    0.94
    👴
    0.87
     grandfather
    0.84
     Grandmother
    0.83
     grandmother
    0.83
     grandpa
    0.82
    Elder
    0.81
     ancianos
    0.81
    Activations Density 0.129%

    No Known Activations