© 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. 9366
    Prev
    Next
    INDEX
    Explanations

    Java package declarations

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

    "package" keyword followed by domain-like names

    np_acts-logits-general · gemini-2.0-flash

    code package declarations

    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
     ſind
    -1.02
     uſed
    -1.02
     Monfieur
    -1.01
     ſever
    -1.01
     ſy
    -0.99
     myſelf
    -0.96
     itſelf
    -0.95
     himſelf
    -0.95
     houſe
    -0.93
     pleaſure
    -0.93
    POSITIVE LOGITS
     com
    0.86
    :
    0.73
     name
    0.73
     main
    0.73
     org
    0.70
     ca
    0.68
     et
    0.68
     i
    0.67
     {
    0.66
     ch
    0.63
    Activations Density 0.051%

    No Known Activations