© 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. 8523
    Prev
    Next
    INDEX
    Explanations

    percentage figures indicating statistical data or significance

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

    P < 0.001 or similar statistical significance

    np_acts-logits-general · gemini-2.0-flash

    statistical significance p-values

    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
    httphttps
    -0.51
    MessageTagHelper
    -0.48
    وفاته
    -0.47
     bio
    -0.45
    bio
    -0.44
    matis
    -0.44
    ådet
    -0.44
     har
    -0.43
    esch
    -0.43
     jabatan
    -0.42
    POSITIVE LOGITS
     propOrder
    0.83
     AssemblyTitle
    0.76
    afficheront
    0.66
     ContentValues
    0.65
     itſelf
    0.65
    Архівовано
    0.64
    enumi
    0.64
    RectangleBorder
    0.63
     myſelf
    0.61
     okuyayım
    0.61
    Activations Density 0.441%

    No Known Activations