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

    Neuronpedia

    Jacobian LensNEW
    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. 34-GEMMASCOPE-RES-16K
    11. 14177
    Prev
    Next
    INDEX
    Explanations

    keywords related to political ideologies, specifically those expressing criticism of political parties and advocating for change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Notwendigkeit
    -0.49
     absolutamente
    -0.48
    很多的
    -0.48
     coger
    -0.47
     utilización
    -0.47
     possibilidades
    -0.46
     andando
    -0.45
     necessidade
    -0.45
     assolutamente
    -0.45
     spowod
    -0.45
    POSITIVE LOGITS
     Reſ
    0.63
     juſ
    0.61
     Conſ
    0.60
     Diſ
    0.59
     Inſ
    0.57
     Jefus
    0.57
     Paglinawan
    0.57
    Conce
    0.55
    tanleria
    0.52
     myſelf
    0.52
    Activations Density 0.789%

    No Known Activations