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. 20-GEMMASCOPE-RES-16K
    6. 149
    Prev
    Next
    INDEX
    Explanations

    information related to property management and operational responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    supervising or managing

    np_acts-logits-general · gemini-2.0-flash

    oversight and management roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    имущества
    -0.60
    zyści
    -0.53
    ineno
    -0.52
     producteurs
    -0.50
     varandra
    -0.50
     travailleurs
    -0.49
     FetchType
    -0.48
     collègues
    -0.48
     pagkak
    -0.47
     alvor
    -0.47
    POSITIVE LOGITS
     oversee
    1.41
     overseeing
    1.37
     oversees
    1.21
     supervise
    1.17
     oversaw
    1.17
     supervising
    1.11
     oversight
    1.09
     coordinating
    1.09
     supervis
    1.08
     coordination
    1.03
    Activations Density 0.443%

    No Known Activations