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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 6672
    Prev
    Next
    INDEX
    Explanations

    words related to nominations and appointments in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.74
    存于互联网档案馆
    -0.71
     שוליים
    -0.64
    
    -0.63
    ViewFeatures
    -0.61
     ویکی‌پدی
    -0.52
    vailable
    -0.50
     parishi
    -0.49
     boarded
    -0.49
     Administrativna
    -0.49
    POSITIVE LOGITS
     nominated
    1.55
     nominate
    1.49
     nomination
    1.44
     appointed
    1.34
     nominating
    1.33
     appoint
    1.29
     appointing
    1.28
     Appointed
    1.26
     elect
    1.25
     Nominations
    1.24
    Activations Density 0.118%

    No Known Activations