© 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. 33-GEMMASCOPE-RES-16K
    11. 10480
    Prev
    Next
    INDEX
    Explanations

    terms associated with marine biology and underwater exploration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rawDesc
    -0.57
     فريبيس
    -0.52
    PreferredItem
    -0.50
    ondissement
    -0.47
     ligiloj
    -0.47
     صوتيه
    -0.44
    Hozzáférés
    -0.44
    Билгалдахарш
    -0.42
    #+#
    -0.40
     StringTokenizer
    -0.40
    POSITIVE LOGITS
     underwater
    1.71
     seabed
    1.44
     submarine
    1.41
     Underwater
    1.37
    underwater
    1.27
     marine
    1.27
     ocean
    1.27
    海底
    1.26
     подвод
    1.23
     submar
    1.21
    Activations Density 0.470%

    No Known Activations