© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 9408
    Prev
    Next
    INDEX
    Explanations

    references to studies and reports related to education and financial statistics

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

    Numbers appearing in reports

    np_acts-logits-general · gemini-2.0-flash

    report of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beginnetje
    -0.71
     يتيمه
    -0.60
     informée
    -0.57
    UnsafeEnabled
    -0.57
    Cyfarwyddwr
    -0.54
     متعلقه
    -0.52
    MockBean
    -0.52
    routeProvider
    -0.52
    Diweddarwch
    -0.52
     Chwiliwch
    -0.52
    POSITIVE LOGITS
     report
    1.12
     Report
    0.92
    report
    0.89
    Report
    0.86
     findings
    0.82
     study
    0.80
    报告
    0.80
     conclusions
    0.72
     published
    0.69
     publication
    0.69
    Activations Density 0.301%

    No Known Activations