Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 7412
    Prev
    Next
    INDEX
    Explanations

    references to political authority and associated actions in the context of governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     providing
    -0.33
    harapkan
    -0.33
    binaan
    -0.32
     romantique
    -0.32
     phun
    -0.32
    ள்ள
    -0.31
     inocente
    -0.30
     Provin
    -0.30
     preciosa
    -0.30
     common
    -0.30
    POSITIVE LOGITS
    rungsseite
    0.71
    Източници
    0.60
     BoxFit
    0.59
    Хьажоргаш
    0.56
    awtextra
    0.54
    RectangleBorder
    0.54
     gynnwys
    0.53
    patine
    0.51
    __*/
    0.51
    verwijspagina
    0.51
    Activations Density 0.039%

    No Known Activations