© 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 EvalsExportsAPI 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. 6320
    Prev
    Next
    INDEX
    Explanations

    code snippets and functions related to Java or programming logic

    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
    ;-)
    -0.50
    点此举报
    -0.47
    …’
    -0.47
     …)
    -0.46
    )».
    -0.46
    ’:
    -0.46
    ,»
    -0.45
    ″
    -0.45
     …”
    -0.45
    ,–
    -0.45
    POSITIVE LOGITS
     everytime
    0.65
     Idk
    0.63
     idk
    0.61
     aswell
    0.59
    tagHelperRunner
    0.57
     functionalities
    0.55
     variabel
    0.55
    puted
    0.55
     variable
    0.55
     values
    0.55
    Activations Density 1.590%

    No Known Activations