© 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. 7-GEMMASCOPE-RES-16K
    11. 13702
    Prev
    Next
    INDEX
    Explanations

    terms related to marine environments and activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     étoit
    -0.54
     Obrador
    -0.44
     auroit
    -0.43
     dafs
    -0.43
     monasteries
    -0.42
    pædia
    -0.41
    FirstResponder
    -0.41
     feroit
    -0.41
    complexContent
    -0.40
     nido
    -0.40
    POSITIVE LOGITS
     Marine
    2.08
     marine
    2.06
    Marine
    2.05
     MARINE
    1.86
    marine
    1.75
     marines
    1.41
     Marines
    1.30
     aquatic
    1.08
    marines
    1.05
     marins
    1.05
    Activations Density 0.273%

    No Known Activations