© 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. 2-GEMMASCOPE-RES-16K
    11. 12403
    Prev
    Next
    INDEX
    Explanations

    key organizations, locations, and notable individuals associated with events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelf
    -0.32
     pleaſure
    -0.30
     viſ
    -0.29
     Autres
    -0.26
     ſta
    -0.26
    ſelves
    -0.26
     fight
    -0.25
     preſent
    -0.25
     ſel
    -0.25
    February
    -0.25
    POSITIVE LOGITS
     يتيمه
    0.97
     noDo
    0.93
     AssemblyCulture
    0.93
     Infórmanos
    0.90
    
    0.88
     invokingState
    0.86
     كومونز
    0.84
     Administrativna
    0.84
    OGND
    0.82
    ViewFeatures
    0.82
    Activations Density 4.379%

    No Known Activations