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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 14321
    Prev
    Next
    INDEX
    Explanations

    mentions of positions of authority and leadership roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новниш
    -0.45
    ritch
    -0.43
     XMLHttpRequest
    -0.42
     bezoek
    -0.40
    forName
    -0.38
    Trigon
    -0.37
    hemi
    -0.37
    esting
    -0.36
     ô
    -0.35
    ⓘ
    -0.35
    POSITIVE LOGITS
     leadership
    2.32
    leadership
    2.06
     lead
    2.05
    Leadership
    1.95
     Leadership
    1.89
     memimpin
    1.89
     leader
    1.86
    lead
    1.84
     LEADERSHIP
    1.77
     leads
    1.76
    Activations Density 0.482%

    No Known Activations