© 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. 9782
    Prev
    Next
    INDEX
    Explanations

    phrases related to legislative processes and legal terminology

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

    Codes, abbreviations, or identifiers starting with a letter

    np_acts-logits-general · gemini-2.0-flash

    doubly robust, DAF, DLJ, DOA, DDA

    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
    SequentialGroup
    -0.61
    KommentareTeilen
    -0.58
     متعلقه
    -0.54
    UnusedPrivate
    -0.51
    +#+#
    -0.50
    oneofs
    -0.48
    帖最后由
    -0.48
     विश्वसनीयता
    -0.46
    CodeAnalysis
    -0.46
    पया
    -0.45
    POSITIVE LOGITS
     DP
    1.19
    DP
    1.14
     DT
    1.14
     DM
    1.14
     DD
    1.10
     DG
    1.09
    DT
    1.09
     DS
    1.09
     DR
    1.07
     DC
    1.07
    Activations Density 2.771%

    No Known Activations