© 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. 41-GEMMASCOPE-RES-16K
    6. 7838
    Prev
    Next
    INDEX
    Explanations

    references to parental relationships and child legitimacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ทุน
    -0.39
     bolsillos
    -0.38
     BoxFit
    -0.37
     tensione
    -0.36
    rasco
    -0.36
     AllMovie
    -0.35
     насељу
    -0.35
     dataTable
    -0.35
    Husband
    -0.35
     Madre
    -0.34
    POSITIVE LOGITS
     born
    1.63
    born
    1.16
    Born
    1.04
     birth
    1.02
     Born
    1.02
     BORN
    1.01
     geboren
    0.96
     conceived
    0.94
     født
    0.93
     lahir
    0.91
    Activations Density 0.474%

    No Known Activations