© 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. 33-GEMMASCOPE-RES-16K
    11. 5569
    Prev
    Next
    INDEX
    Explanations

    dialog or conversational elements within a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NES
    -0.46
    MIL
    -0.46
     Nes
    -0.44
     Pls
    -0.44
     pls
    -0.44
     Waz
    -0.43
     bays
    -0.43
     PAM
    -0.43
     Alger
    -0.42
    ieden
    -0.42
    POSITIVE LOGITS
     yeah
    1.48
    Yeah
    1.42
     Yeah
    1.37
    yeah
    1.23
     YEAH
    1.02
    Yea
    0.92
    是啊
    0.89
     yep
    0.87
    Yep
    0.86
     yea
    0.84
    Activations Density 0.128%

    No Known Activations