© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3788
    Prev
    Next
    INDEX
    Explanations

    capital letters at the beginning of words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Token "s" followed by various letters

    np_acts-logits-general · gemini-2.0-flash

    words starting with s

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.61
    ArgumentParser
    -0.60
    IntoConstraints
    -0.57
    Życiorys
    -0.55
    SharedCtor
    -0.54
    AndEndTag
    -0.54
     Unies
    -0.53
    InjectMocks
    -0.53
    SequentialGroup
    -0.52
    /*---
    -0.51
    POSITIVE LOGITS
     Enchanted
    0.55
    Viitteet
    0.54
     présentés
    0.54
     fleuve
    0.52
     kveld
    0.50
     sposa
    0.50
     cesse
    0.49
     traditionnels
    0.49
     jspb
    0.49
     soprav
    0.49
    Activations Density 0.268%

    No Known Activations