© 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. 34-GEMMASCOPE-RES-16K
    11. 12949
    Prev
    Next
    INDEX
    Explanations

    phrases that express confusion or inquiry about what is happening

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.62
    orghini
    -0.54
    enumii
    -0.52
     propOrder
    -0.51
     незавершена
    -0.48
     CreateTagHelper
    -0.47
    caler
    -0.47
    JsonInclude
    -0.47
    はじめに
    -0.47
     chande
    -0.47
    POSITIVE LOGITS
    Tikang
    0.44
    Diweddarwch
    0.36
    Ongoing
    0.35
    velocityX
    0.32
    pustakaan
    0.32
    |()
    0.31
     apapun
    0.31
     dzie
    0.30
     commotion
    0.30
    ībā
    0.30
    Activations Density 0.122%

    No Known Activations