© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 992
    Prev
    Next
    INDEX
    Explanations

    references to official reports and guidelines in the context of policy and research

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

    Preceding tokens of the word "report"

    np_acts-logits-general · gemini-2.0-flash

    official reports

    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
    NoSuch
    -0.53
    expandindo
    -0.52
    verwijspagina
    -0.47
    ाहरण
    -0.47
    opardy
    -0.47
     Physiol
    -0.45
    AnchorTagHelper
    -0.45
     antigos
    -0.45
    ukone
    -0.44
     attiva
    -0.43
    POSITIVE LOGITS
     report
    2.02
     Report
    1.63
    report
    1.62
    Report
    1.47
     REPORT
    1.40
     reports
    1.28
     study
    1.24
     relatório
    1.21
    REPORT
    1.17
    报告
    1.17
    Activations Density 0.380%

    No Known Activations