© 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. 3762
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to programming components and class structures in various coding languages

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

    Code snippets (possibly React or Python)

    np_acts-logits-general · gemini-2.0-flash

    SEM, mean, ±

    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
     EconPapers
    -0.52
     unseen
    -0.40
     forces
    -0.38
    DoNot
    -0.37
     pop
    -0.37
    UrlEncoded
    -0.37
    馃
    -0.36
    ClInclude
    -0.36
     Wikiseite
    -0.36
    uracy
    -0.36
    POSITIVE LOGITS
     StatefulWidget
    1.33
     StatelessWidget
    0.94
    IContainer
    0.71
    ViewInit
    0.63
    TypedDataSet
    0.60
     Component
    0.59
    OrNil
    0.59
    ThroughAttribute
    0.57
     Autorizaciones
    0.57
    SourceChecksum
    0.56
    Activations Density 0.011%

    No Known Activations