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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12423
    Prev
    Next
    INDEX
    Explanations

    underscored words or identifiers in programming contexts

    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
    writeFieldEnd
    -0.61
     suivantes
    -0.54
     seguinte
    -0.53
    InputTagHelper
    -0.51
    原始内容存档于
    -0.50
     Inſ
    -0.49
    AddTagHelper
    -0.48
     informée
    -0.47
     suivants
    -0.46
     Diſ
    -0.46
    POSITIVE LOGITS
    sizeCache
    0.51
     uLocal
    0.47
    Tikang
    0.47
     createContext
    0.42
     FetchType
    0.42
    ImageContext
    0.41
     nonatomic
    0.41
     crossorigin
    0.38
     تكبرها
    0.37
     Autorisations
    0.37
    Activations Density 1.126%

    No Known Activations