© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14745
    Prev
    Next
    INDEX
    Explanations

    references to technical specifications and programming commands related to software and digital content

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

    after opening parenthesis

    np_acts-logits-general · gemini-2.0-flash

    form . but then may on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новниш
    -0.60
    RegressionTest
    -0.47
     Wach
    -0.45
     OCCUP
    -0.42
     Cur
    -0.42
     Welfare
    -0.42
     resultCode
    -0.42
    hamcrest
    -0.41
     cur
    -0.41
    staff
    -0.41
    POSITIVE LOGITS
     estekak
    0.65
    URLException
    0.47
    AutoresizingMask
    0.42
     BrowserModule
    0.40
    -------
    0.39
     digitais
    0.39
    jména
    0.38
     sprend
    0.38
     ddelweddau
    0.38
     oplossing
    0.37
    Activations Density 0.799%

    No Known Activations