© 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-2-9B
    7. Residual Stream - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 8574
    Prev
    Next
    INDEX
    Explanations

    pronouns, specifically first-person and third-person references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    хьтан
    -0.81
     okuyayım
    -0.74
     propOrder
    -0.72
     gyhoeddwyd
    -0.71
    httphttps
    -0.71
     Italijanski
    -0.71
     ujednoznacz
    -0.70
    Хьажоргаш
    -0.69
     disambiguazione
    -0.69
     Chwiliwch
    -0.68
    POSITIVE LOGITS
     had
    0.59
     they
    0.55
     never
    0.53
     didn
    0.51
     has
    0.50
     have
    0.50
     hadn
    0.49
     can
    0.49
    They
    0.47
     only
    0.46
    Activations Density 0.461%

    No Known Activations