© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7400
    Prev
    Next
    INDEX
    Explanations

    mentions of something being interesting or noteworthy

    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
    Goal
    -0.49
    ViewImports
    -0.47
     IFTT
    -0.44
    Goals
    -0.43
     Goal
    -0.43
    PMailer
    -0.43
    copg
    -0.42
     Roskov
    -0.42
    VersionUID
    -0.40
    GEBURTSDATUM
    -0.39
    POSITIVE LOGITS
     interesting
    1.69
    interesting
    1.58
     Interesting
    1.55
    Interesting
    1.54
     interesante
    1.36
     intéressante
    1.35
     interessante
    1.31
     cieka
    1.27
     zajíma
    1.25
     intriguing
    1.23
    Activations Density 0.209%

    No Known Activations