© 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. 40-GEMMASCOPE-RES-16K
    11. 1838
    Prev
    Next
    INDEX
    Explanations

    relationships and emotional connections between family members

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.40
    mobileqq
    -0.39
    iranje
    -0.33
    ereich
    -0.32
    .*")]
    -0.32
     }^{[
    -0.32
    sqcup
    -0.32
    prefixer
    -0.31
    testens
    -0.31
    chargez
    -0.31
    POSITIVE LOGITS
     mother
    3.34
     mom
    3.13
     mothers
    2.97
     parents
    2.94
     Mom
    2.89
     parent
    2.83
     Mother
    2.80
     moms
    2.80
    mother
    2.75
    Mother
    2.72
    Activations Density 1.417%

    No Known Activations