© 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. 5707
    Prev
    Next
    INDEX
    Explanations

    references to community support and healthcare involvement

    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
     mergeFrom
    -0.47
    inghouse
    -0.45
    ništ
    -0.40
     kişinin
    -0.40
    aulted
    -0.40
     човек
    -0.40
     <<<<<<<<<<<<<<
    -0.40
     człowie
    -0.39
     człowiek
    -0.38
     kişi
    -0.37
    POSITIVE LOGITS
     families
    0.91
     ourselves
    0.87
     yourself
    0.83
     yourselves
    0.78
    families
    0.77
     myself
    0.75
     YOURSELF
    0.75
     familles
    0.72
    yourself
    0.69
     herself
    0.68
    Activations Density 0.339%

    No Known Activations