© 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. 36-GEMMASCOPE-RES-16K
    6. 7365
    Prev
    Next
    INDEX
    Explanations

    references to political issues and social stances, particularly regarding democratic values and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     idéia
    -0.46
    esistenza
    -0.43
     Audiodateien
    -0.40
     estampa
    -0.39
     Gegend
    -0.39
     realidade
    -0.39
     caminhada
    -0.37
     existência
    -0.37
     Akte
    -0.36
    vânt
    -0.36
    POSITIVE LOGITS
     immigration
    1.30
    immigration
    1.05
     Immigration
    1.05
     taxation
    1.04
     immig
    1.01
     unemployment
    0.99
    Immigration
    0.98
     refugees
    0.97
     refugee
    0.96
     electoral
    0.95
    Activations Density 1.070%

    No Known Activations