© 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. 10-GEMMASCOPE-RES-16K
    11. 6909
    Prev
    Next
    INDEX
    Explanations

    words and phrases emphasizing "super" or "ultra," often in the context of describing exceptional qualities or performance

    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
     chemins
    -0.43
    sieh
    -0.43
     Jars
    -0.42
    ories
    -0.42
     Paths
    -0.42
     sentada
    -0.40
     Waltz
    -0.40
    scri
    -0.39
    hesis
    -0.39
    Dough
    -0.39
    POSITIVE LOGITS
     super
    2.38
     Super
    2.09
     SUPER
    2.02
    Super
    2.02
    super
    2.00
    SUPER
    1.80
     супер
    1.66
     súper
    1.59
    超级
    1.52
    Супер
    1.45
    Activations Density 0.151%

    No Known Activations