© 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. 37-GEMMASCOPE-RES-16K
    11. 4533
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases related to giving, helping, or making things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.44
    PropertyChanging
    -0.42
     οποία
    -0.41
    PointerException
    -0.39
     toch
    -0.36
     він
    -0.35
     épaules
    -0.35
     której
    -0.34
     используя
    -0.33
     restantes
    -0.32
    POSITIVE LOGITS
     plenty
    1.13
     lots
    1.09
     beaucoup
    0.93
     LOTS
    0.90
     alot
    0.88
     many
    0.87
     loads
    0.82
     banyak
    0.82
    plenty
    0.82
     enough
    0.80
    Activations Density 0.783%

    No Known Activations