© 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. 8-GEMMASCOPE-RES-16K
    11. 7050
    Prev
    Next
    INDEX
    Explanations

    terms related to marine biology, particularly focusing on deep-sea sponges and their ecological context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     föl
    -0.39
     quoique
    -0.34
     obwohl
    -0.34
     būtų
    -0.33
     secado
    -0.32
    ÍSTICAS
    -0.31
     giang
    -0.31
    madamente
    -0.30
     davantage
    -0.30
     définitivement
    -0.29
    POSITIVE LOGITS
     seabed
    0.73
     MainAxisSize
    0.72
     offshore
    0.69
     ocean
    0.66
    IBOutlet
    0.66
    Offshore
    0.65
    waitKey
    0.63
     underwater
    0.62
     submarine
    0.62
     Oceanography
    0.60
    Activations Density 0.387%

    No Known Activations