© 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. 11-GEMMASCOPE-RES-16K
    11. 13442
    Prev
    Next
    INDEX
    Explanations

    different forms and contexts of the word "letter."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    makeConstraints
    -0.99
     propOrder
    -0.88
    Lähteet
    -0.87
     Roskov
    -0.81
    hehehe
    -0.78
    uesday
    -0.75
    Alike
    -0.75
    mylist
    -0.73
    Verweise
    -0.72
    tablissement
    -0.71
    POSITIVE LOGITS
     letters
    1.74
     Letters
    1.61
    Letters
    1.49
     LETTER
    1.48
     letter
    1.47
     Letter
    1.45
    letter
    1.41
    letters
    1.38
     LETTERS
    1.37
    Letter
    1.35
    Activations Density 0.078%

    No Known Activations