© 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. 35-GEMMASCOPE-RES-16K
    11. 7472
    Prev
    Next
    INDEX
    Explanations

    expressions of interest and willingness to collaborate or assist

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ceğine
    -0.53
    yntaxException
    -0.45
    
    -0.45
     creemos
    -0.41
     creen
    -0.41
    LabelTagHelper
    -0.38
     crees
    -0.36
    untut
    -0.35
     refiri
    -0.35
     preocupes
    -0.35
    POSITIVE LOGITS
     willing
    1.75
    willing
    1.70
     willingness
    1.61
    Willing
    1.60
     Willing
    1.57
     willingly
    1.51
     gladly
    1.48
    願意
    1.12
    愿意
    1.11
     happily
    1.04
    Activations Density 0.329%

    No Known Activations