© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 9801
    Prev
    Next
    INDEX
    Explanations

    phrases related to equitable and mutually beneficial outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abstractmethod
    -0.41
     MediatR
    -0.39
    ymal
    -0.37
    HomeAsUp
    -0.37
    toprule
    -0.37
     lasers
    -0.36
    IGraph
    -0.36
    (",",
    -0.36
    下一篇
    -0.35
     sug
    -0.35
    POSITIVE LOGITS
    WriteTagHelper
    0.49
     beneficia
    0.48
    yntaxException
    0.47
     vantaggi
    0.47
    benef
    0.46
    ýchod
    0.46
     benefit
    0.45
    Benefit
    0.45
    benefit
    0.44
     Mutual
    0.43
    Activations Density 0.373%

    No Known Activations