© 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. 13994
    Prev
    Next
    INDEX
    Explanations

    specific programming and technical syntax or terminology related to coding and data processing

    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
    :✨
    -0.61
    COMPLE
    -0.58
    delwed
    -0.58
    further
    -0.55
    webElementXpaths
    -0.54
    COMPLETED
    -0.53
    Kole
    -0.51
    Jeografia
    -0.50
    Comple
    -0.50
    Completion
    -0.47
    POSITIVE LOGITS
     cont
    1.63
     contin
    1.54
     CONTIN
    1.52
     continuous
    1.48
     Contin
    1.39
     Cont
    1.38
     conti
    1.38
    Cont
    1.37
     continuo
    1.36
    cont
    1.33
    Activations Density 0.373%

    No Known Activations