© 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. 4262
    Prev
    Next
    INDEX
    Explanations

    references to coding or programming-related contexts, especially in relation to continuous integration or artificial saliva formulations

    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
    InitVars
    -0.47
    ">//
    -0.43
    batim
    -0.42
     hablado
    -0.42
     harmon
    -0.39
     Gegenteil
    -0.39
    Snap
    -0.38
    исленность
    -0.38
     Auß
    -0.38
     recogn
    -0.38
    POSITIVE LOGITS
    ci
    0.80
    CI
    0.62
    bot
    0.62
     bot
    0.61
     rig
    0.56
     salad
    0.55
     Bot
    0.54
     clusters
    0.52
     salads
    0.52
     bots
    0.51
    Activations Density 0.548%

    No Known Activations