© 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. 35-GEMMASCOPE-RES-16K
    11. 7422
    Prev
    Next
    INDEX
    Explanations

    causal relationships and their absence in various contexts, particularly in health and scientific studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PMailer
    -0.40
     propOrder
    -0.38
     Administrativna
    -0.38
    PerformLayout
    -0.36
     Palli
    -0.35
    GEBURTSDATUM
    -0.35
     виправивши
    -0.35
    انتهای
    -0.35
    asilkan
    -0.34
    pdu
    -0.34
    POSITIVE LOGITS
     connection
    2.31
     link
    2.22
     connections
    2.05
     links
    2.03
     linking
    1.97
     linkage
    1.94
     correlation
    1.91
     linkages
    1.87
     association
    1.86
    connection
    1.84
    Activations Density 2.149%

    No Known Activations