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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 1043
    Prev
    Next
    INDEX
    Explanations

    terms related to delegation and representative functions

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

    delegation, contingent, relegated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     África
    -0.38
     picante
    -0.38
     is
    -0.37
     Ambiental
    -0.37
    Wiener
    -0.36
    Ready
    -0.34
     Winf
    -0.34
    s
    -0.34
     sûre
    -0.34
    RequiresApi
    -0.34
    POSITIVE LOGITS
     Delegation
    1.17
     delegation
    1.06
     delegations
    1.02
     Deleg
    0.99
    deleg
    0.96
     deleg
    0.86
     Delegates
    0.80
     laſſen
    0.79
    gation
    0.76
     Delegate
    0.75
    Activations Density 0.002%

    No Known Activations