© 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. 8300
    Prev
    Next
    INDEX
    Explanations

    references to stem-related concepts and their properties in various contexts

    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
     XJ
    -0.84
    JET
    -0.84
     Jof
    -0.81
     defaultstate
    -0.79
    Jet
    -0.78
     JET
    -0.78
     Jojo
    -0.76
     Joc
    -0.75
     Jet
    -0.74
    JJ
    -0.73
    POSITIVE LOGITS
     rozwój
    0.63
     hospod
    0.55
     keberadaan
    0.52
     the
    0.50
     liknande
    0.48
     turístico
    0.47
     velik
    0.47
     dlouho
    0.47
     Steen
    0.47
     Ursprung
    0.46
    Activations Density 1.817%

    No Known Activations