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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3761
    Prev
    Next
    INDEX
    Explanations

    references to delegation and outsourcing in operational contexts

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

    Transferring responsibility/authority

    np_acts-logits-general · gemini-2.0-flash

    handing over responsibility or control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.57
     informée
    -0.42
    Hozzáférés
    -0.41
    OGND
    -0.40
     lenker
    -0.40
    RTHOOK
    -0.39
    BASEPATH
    -0.39
    ✭✭
    -0.39
    
    -0.38
    JvmStatic
    -0.37
    POSITIVE LOGITS
     entrusted
    0.79
     entrust
    0.78
     delegated
    0.77
     handover
    0.75
     delegation
    0.69
     handing
    0.64
    交给
    0.62
     handed
    0.61
    deleg
    0.61
     Delegation
    0.60
    Activations Density 0.449%

    No Known Activations