© 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. 3949
    Prev
    Next
    INDEX
    Explanations

    references to dietary patterns and their classifications

    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
    AddTagHelper
    -0.73
    UnusedPrivate
    -0.57
    ftagPool
    -0.52
    URLException
    -0.52
    oa̍t
    -0.47
    uxxxx
    -0.47
     estadounid
    -0.47
    #
    -0.47
     kolei
    -0.47
     متعلقه
    -0.45
    POSITIVE LOGITS
      
    0.43
    laceae
    0.38
     helical
    0.35
    出版年
    0.35
    ziasztok
    0.34
    下手
    0.34
     cauza
    0.34
     springfox
    0.34
    InBytes
    0.33
    RegistryLite
    0.33
    Activations Density 1.059%

    No Known Activations