© 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. 9-GEMMASCOPE-RES-16K
    11. 11376
    Prev
    Next
    INDEX
    Explanations

    references to the sky and celestial themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to the sky, celestial elements, and heavens.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.45
     peça
    -0.39
     VW
    -0.39
    achios
    -0.38
    otoxin
    -0.35
     ditto
    -0.34
     broek
    -0.34
     pezzo
    -0.34
    nettes
    -0.34
     parts
    -0.33
    POSITIVE LOGITS
     sky
    2.13
     Sky
    2.03
    Sky
    1.96
     SKY
    1.80
    sky
    1.62
     skies
    1.52
    SKY
    1.49
     Skies
    1.40
     skys
    1.40
     cielo
    1.38
    Activations Density 0.065%

    No Known Activations