© 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. 4161
    Prev
    Next
    INDEX
    Explanations

    various forms of punctuation and expressive emotions in text

    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
     especially
    -0.50
     Especially
    -0.40
     zwłaszcza
    -0.38
    especially
    -0.36
    Especially
    -0.35
     particularly
    -0.34
     Особенно
    -0.34
    собенно
    -0.33
    pecially
    -0.33
     особенно
    -0.32
    POSITIVE LOGITS
    Sounds
    1.21
     Sounds
    1.19
     Wow
    1.14
    Yikes
    1.13
    Ouch
    1.11
     wow
    1.09
    Wow
    1.09
    sounds
    1.08
     yep
    1.06
     sounds
    1.05
    Activations Density 0.530%

    No Known Activations