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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15345
    Prev
    Next
    INDEX
    Explanations

    references to celestial and heavenly concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    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
    -0.41
     VW
    -0.38
     peça
    -0.37
    formin
    -0.35
     Edit
    -0.35
    ing
    -0.35
    erializer
    -0.35
    ictwa
    -0.32
    emplares
    -0.32
     Move
    -0.32
    POSITIVE LOGITS
     sky
    1.78
     Sky
    1.67
    Sky
    1.63
     SKY
    1.50
     skies
    1.33
    sky
    1.30
     heaven
    1.30
     cielo
    1.30
     Heaven
    1.28
    Heaven
    1.28
    Activations Density 0.179%

    No Known Activations