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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7260
    Prev
    Next
    INDEX
    Explanations

    references to celestial bodies and space themes

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

    Japanese anime or manga terms and cosmic/space-related imagery.

    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
     Autorisations
    -0.42
    WebElementEntity
    -0.41
    ilever
    -0.40
    tagPool
    -0.38
    MessageTagHelper
    -0.37
     &___
    -0.36
    phosa
    -0.36
    TagMode
    -0.35
    inander
    -0.35
     mężczyzn
    -0.35
    POSITIVE LOGITS
     cosmic
    1.15
     astronomers
    1.02
     astro
    1.02
    cosmic
    1.02
     galaxy
    1.02
    Astro
    1.00
    Cosmic
    0.96
    Astronom
    0.96
     Astro
    0.96
     Universe
    0.95
    Activations Density 0.500%

    No Known Activations