© 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. 7103
    Prev
    Next
    INDEX
    Explanations

    statements or comments made by officials or representatives

    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
     ब्रेकडाउन
    -0.61
     незавершена
    -0.57
    ագրություններ
    -0.55
    parsedMessage
    -0.54
     noDo
    -0.52
    IUrlHelper
    -0.52
    AddAttribute
    -0.49
     createState
    -0.49
    httphttps
    -0.47
     Houſe
    -0.47
    POSITIVE LOGITS
    Apart
    0.80
     apart
    0.76
    apart
    0.70
     Apart
    0.70
     majority
    0.61
    Majority
    0.59
    Hence
    0.56
     Hence
    0.53
    Sudah
    0.53
     Incidentally
    0.53
    Activations Density 0.071%

    No Known Activations