© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 7002
    Prev
    Next
    INDEX
    Explanations

    politically charged adjectives and descriptions of authoritarianism

    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
    wapV
    -0.41
    miyorum
    -0.37
    //
    -0.35
     Hoek
    -0.35
    nmgp
    -0.35
    canestro
    -0.35
    BagConstraints
    -0.33
    HasIndex
    -0.33
    RTEX
    -0.33
    entibus
    -0.32
    POSITIVE LOGITS
     authoritarian
    1.23
     dictatorship
    1.19
     totalitarian
    1.13
     despotism
    1.09
     auto
    1.09
     dictators
    1.05
     dict
    1.02
     despo
    1.01
     tyrannical
    1.00
     tyranny
    1.00
    Activations Density 0.736%

    No Known Activations