© 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. 25-GEMMASCOPE-RES-16K
    11. 15963
    Prev
    Next
    INDEX
    Explanations

    references to articles and research papers, particularly in the field of physics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/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.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    processable
    -0.68
    SharedCtor
    -0.66
    ConstraintMaker
    -0.65
    principalTable
    -0.65
    ReusableCell
    -0.64
    stateProvider
    -0.62
    tagHelperRunner
    -0.61
     AspNetCore
    -0.60
    /**
    -0.60
     onOptions
    -0.59
    POSITIVE LOGITS
    arXiv
    1.56
     arXiv
    0.71
    arxiv
    0.58
     arxiv
    0.56
     draft
    0.49
     Draft
    0.38
     preprint
    0.36
     circulating
    0.35
     draught
    0.33
     Arxiv
    0.31
    Activations Density 0.237%

    No Known Activations