© 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-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 2580
    Prev
    Next
    INDEX
    Explanations

    mentions of familial relationships, particularly focusing on siblings and brothers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Население
    -0.39
    ceptre
    -0.38
     manifiesto
    -0.38
     словарь
    -0.36
     broad
    -0.36
     Stoke
    -0.36
     köp
    -0.35
     Kirkwood
    -0.34
    ätigung
    -0.34
    MADRID
    -0.34
    POSITIVE LOGITS
    Brothers
    1.15
     Brothers
    1.14
     Sisters
    1.06
     BROTHERS
    1.05
    brothers
    1.05
     sisters
    1.02
    Sisters
    1.00
    sisters
    0.98
     Bros
    0.95
     brothers
    0.94
    Activations Density 0.081%

    No Known Activations