© 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. 11-GEMMASCOPE-RES-16K
    11. 8373
    Prev
    Next
    INDEX
    Explanations

    function signatures and type definitions in programming-related text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.46
     protoimpl
    -0.39
     invokingState
    -0.37
     actionMode
    -0.35
     pintada
    -0.33
    NamedQueries
    -0.32
     ujednoznacz
    -0.32
     otomatig
    -0.32
    fällig
    -0.32
     dichiarato
    -0.31
    POSITIVE LOGITS
    DockStyle
    0.63
    HasAnnotation
    0.51
     segno
    0.47
    applied
    0.46
    Pranala
    0.46
    UserScript
    0.46
     Counselling
    0.45
     lectures
    0.45
     mercury
    0.44
    Enllaços
    0.44
    Activations Density 0.778%

    No Known Activations