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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8730
    Prev
    Next
    INDEX
    Explanations

    terms related to summaries or summary judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SpringRunner
    -0.59
    SharedDtor
    -0.56
    readFileSync
    -0.56
     CascadeType
    -0.56
     JpaRepository
    -0.56
    AutoField
    -0.52
    InputTagHelper
    -0.52
     AttributeSet
    -0.52
     pylint
    -0.51
     Prefix
    -0.51
    POSITIVE LOGITS
     summary
    1.10
    Summary
    1.02
     Summary
    1.00
     SUMMARY
    0.83
    summary
    0.82
    SUMMARY
    0.79
     summarize
    0.73
     summarizes
    0.71
     summarized
    0.68
    Abstract
    0.68
    Activations Density 0.066%

    No Known Activations