© 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. 38-GEMMASCOPE-RES-16K
    11. 9801
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or equations involving variables and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.63
    StoryboardSegue
    -0.59
    WriteTagHelper
    -0.54
    AddTagHelper
    -0.54
     ujednoznacz
    -0.52
    oa̍t
    -0.52
    Filmographie
    -0.51
    msgTypes
    -0.51
     հղումներ
    -0.50
    numerusform
    -0.50
    POSITIVE LOGITS
     Since
    0.74
     Notice
    0.70
     notice
    0.69
    Since
    0.67
     since
    0.65
     Let
    0.65
     Now
    0.63
    $\
    0.63
     $\
    0.63
    Notice
    0.61
    Activations Density 3.580%

    No Known Activations