© 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. 15-GEMMASCOPE-RES-16K
    6. 2042
    Prev
    Next
    INDEX
    Explanations

    declarations of functions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BrowserModule
    -0.64
    Personensuche
    -0.63
     Photocase
    -0.60
     MainAxisSize
    -0.54
    protoc
    -0.52
     légales
    -0.51
     незавершена
    -0.50
    Хьажоргаш
    -0.50
    AddHtmlAttribute
    -0.50
    principalTable
    -0.50
    POSITIVE LOGITS
    function
    0.90
     function
    0.90
    Function
    0.61
     Function
    0.56
     Funktion
    0.46
     functions
    0.44
    FUNCTION
    0.44
    Funktion
    0.43
     FUNCTION
    0.43
    Mej
    0.43
    Activations Density 0.047%

    No Known Activations