© 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. 41-GEMMASCOPE-RES-16K
    11. 10707
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "mist" and references to specific structures or types in various contexts, indicating a focus on errors or mistakes within narratives or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Eldridge
    -0.56
     SLC
    -0.55
     Clancy
    -0.48
     Elen
    -0.47
     Blanca
    -0.47
    elm
    -0.45
     Bloomberg
    -0.44
    PLC
    -0.43
     elm
    -0.43
    Elen
    -0.43
    POSITIVE LOGITS
     Leal
    0.94
     Bernal
    0.90
    Neal
    0.90
     Rosal
    0.90
     Neal
    0.89
     Kowal
    0.87
     Grimal
    0.85
     Beal
    0.85
     Kemal
    0.85
    aral
    0.84
    Activations Density 1.067%

    No Known Activations