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-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10690
    Prev
    Next
    INDEX
    Explanations

    terms related to mediation and intermediaries in various contexts

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

    Texts containing the word "mediation"

    np_acts-logits-general · gemini-2.0-flash

    mediation and intermediaries

    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
     nonUne
    -0.55
    ViewFeatures
    -0.49
     EconPapers
    -0.48
    Liberty
    -0.47
     MongoClient
    -0.46
    WireFormatLite
    -0.44
    uerre
    -0.44
     Liberty
    -0.44
    MergeFrom
    -0.43
    ivotopis
    -0.43
    POSITIVE LOGITS
     intermediary
    1.16
     mediating
    1.05
     intermediaries
    1.05
     mediator
    1.00
     mediate
    0.98
     intermedi
    0.96
     mediators
    0.96
     mediation
    0.96
     intermediate
    0.89
     mediates
    0.89
    Activations Density 0.523%

    No Known Activations