© 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. 16-GEMMASCOPE-RES-16K
    11. 13485
    Prev
    Next
    INDEX
    Explanations

    references to specific targets or objectives in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     createdBy
    -0.44
     rowCount
    -0.44
    isler
    -0.43
    őben
    -0.43
    isClosed
    -0.42
    nungen
    -0.41
    knex
    -0.40
     ondu
    -0.40
    échange
    -0.40
     pernikahan
    -0.39
    POSITIVE LOGITS
     target
    1.61
     Target
    1.58
    target
    1.57
    Target
    1.52
     TARGET
    1.45
    getTarget
    1.36
    TARGET
    1.33
     getTarget
    1.33
     targets
    1.28
     Targets
    1.27
    Activations Density 0.056%

    No Known Activations