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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 5981
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives and phrases indicating superiority or extremity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 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
     nice
    -0.65
    bilang
    -0.61
    Controllo
    -0.61
    Altri
    -0.59
     poco
    -0.59
     weiterer
    -0.56
    不错的
    -0.54
     دیکھیے
    -0.52
     ujednoznacz
    -0.52
     molto
    -0.52
    POSITIVE LOGITS
     healthiest
    1.33
     safest
    1.31
     happiest
    1.24
     greatest
    1.23
    iest
    1.23
    ariest
    1.22
     freshest
    1.18
     heaviest
    1.18
     strongest
    1.17
    greatest
    1.17
    Activations Density 0.504%

    No Known Activations