© 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. 37-GEMMASCOPE-RES-16K
    11. 4083
    Prev
    Next
    INDEX
    Explanations

    key attributes and qualities related to performance and experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.67
     autorytatywna
    -0.66
     propOrder
    -0.58
    XmlAccessType
    -0.54
    IsContent
    -0.47
    Personendaten
    -0.47
    oredCriteria
    -0.47
    WaitGroup
    -0.47
    səhifə
    -0.46
    sizeCache
    -0.45
    POSITIVE LOGITS
     unmatched
    1.41
     unsurpassed
    1.34
     rival
    1.28
     unrival
    1.28
     second
    1.27
     unrivalled
    1.23
     unparalleled
    1.23
     surpassed
    1.15
     rivals
    1.13
    second
    1.08
    Activations Density 0.387%

    No Known Activations