© 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. 8585
    Prev
    Next
    INDEX
    Explanations

    legal and organizational terminology associated with policy and regulatory conduct

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

    Acronyms and initialisms

    np_acts-logits-general · gemini-2.0-flash

    acronyms following parentheses

    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
    -0.84
     raiſ
    -0.70
     ſever
    -0.69
     Monfieur
    -0.69
     jsPsych
    -0.68
     ſeveral
    -0.66
     nahilalakip
    -0.65
     Paglinawan
    -0.65
     pleaſure
    -0.64
    oredCriteria
    -0.63
    POSITIVE LOGITS
     RT
    0.98
     MT
    0.96
     Kot
    0.92
     PT
    0.91
    RT
    0.91
    pt
    0.90
    rt
    0.90
    WT
    0.89
    BT
    0.89
     GT
    0.89
    Activations Density 1.382%

    No Known Activations