© 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. 27-GEMMASCOPE-RES-16K
    11. 8737
    Prev
    Next
    INDEX
    Explanations

    terms associated with specific medical conditions and their complications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/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.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doInBackground
    -0.73
    хьтан
    -0.64
    ConstraintMaker
    -0.61
    findpost
    -0.59
    StoryboardSegue
    -0.58
     незавершена
    -0.57
    DataBinding
    -0.53
     viewDidLoad
    -0.52
    RTEE
    -0.51
     AppDelegate
    -0.50
    POSITIVE LOGITS
     common
    0.66
     causes
    0.65
    common
    0.60
    常见
    0.59
     commonly
    0.57
     rare
    0.55
     causas
    0.54
     rarest
    0.52
    Common
    0.52
     cause
    0.51
    Activations Density 0.933%

    No Known Activations