© 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-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 11580
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships, particularly involving sons and daughters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wahati
    -0.67
     kaarangay
    -0.64
    tinyos
    -0.62
    extAlignment
    -0.59
    ErrUnexpectedEOF
    -0.57
    addPreferred
    -0.57
    jooq
    -0.57
    揄
    -0.57
     للمعارف
    -0.57
    ornos
    -0.56
    POSITIVE LOGITS
     daughter
    1.41
     Daughter
    1.29
    Daughter
    1.27
     son
    1.15
     daughters
    1.14
    daughter
    1.05
     sons
    1.00
     Son
    1.00
     Tochter
    1.00
     dochter
    0.99
    Activations Density 0.165%

    No Known Activations