© 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. 3-GEMMASCOPE-RES-16K
    11. 5830
    Prev
    Next
    INDEX
    Explanations

    references to structured plans or organized initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    astify
    -0.57
    TintMode
    -0.56
    setVerticalGroup
    -0.52
    istoitu
    -0.47
    enderror
    -0.47
    InputBorder
    -0.45
    annica
    -0.45
    LookAnd
    -0.45
    OGND
    -0.43
     useAppContext
    -0.43
    POSITIVE LOGITS
    Enabled
    0.85
     Programme
    0.75
     Programmes
    0.71
    Programme
    0.71
     PROGRAMME
    0.70
    programme
    0.68
     programme
    0.66
     programmes
    0.66
    enabled
    0.64
     Screening
    0.63
    Activations Density 0.054%

    No Known Activations