© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1739
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships, specifically focusing on brothers and siblings

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

    siblings or family relations

    np_acts-logits-general · gemini-2.0-flash

    brothers and sisters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atürk
    -0.45
    Kunden
    -0.41
    Bags
    -0.41
     blobs
    -0.40
    representative
    -0.40
     bourgeo
    -0.39
     Seat
    -0.38
    Donut
    -0.38
     mę
    -0.38
    ãng
    -0.38
    POSITIVE LOGITS
     brothers
    1.24
     brother
    1.23
     sisters
    1.20
     sibling
    1.19
     sister
    1.19
     siblings
    1.14
    brothers
    1.05
    brother
    1.02
     kardeş
    1.02
     Brothers
    0.99
    Activations Density 0.207%

    No Known Activations