© 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. 39-GEMMASCOPE-RES-16K
    6. 5059
    Prev
    Next
    INDEX
    Explanations

    negative sentiments directed towards authority and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ManagedBean
    -0.54
     Photocase
    -0.47
    writeFieldEnd
    -0.46
     الرياضيه
    -0.43
    hyrchwyd
    -0.43
    IBOutlet
    -0.43
     вікісторінку
    -0.42
     صوتيه
    -0.41
     InputDecoration
    -0.40
    delwed
    -0.40
    POSITIVE LOGITS
     repressive
    1.25
     repression
    1.24
     oppressive
    1.05
     suppression
    1.03
     authoritarian
    0.98
     oppression
    0.95
     repres
    0.91
     crackdown
    0.90
     suppressing
    0.89
     repress
    0.87
    Activations Density 0.926%

    No Known Activations