© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 8733
    Prev
    Next
    INDEX
    Explanations

    specific terms related to data structures and computer programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dis
    -0.24
     dis
    -0.24
    робнее
    -0.23
    makeText
    -0.23
     Bu
    -0.21
     ph
    -0.21
     W
    -0.20
     trans
    -0.20
                           
    -0.20
     te
    -0.20
    POSITIVE LOGITS
     ivelany
    0.79
    principalColumn
    0.75
     незавершена
    0.75
    StoryboardSegue
    0.73
     мәкал
    0.72
     esternos
    0.71
    */),
    0.69
    enablog
    0.69
     ostavi
    0.68
     autorytatywna
    0.68
    Activations Density 1.651%

    No Known Activations