© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15724
    Prev
    Next
    INDEX
    Explanations

    references to lists or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    tagHelperRunner
    -0.46
    InjectAttribute
    -0.36
     Meksiku
    -0.36
    çants
    -0.36
    Източници
    -0.36
    PropertyChanging
    -0.35
    InstrumentedTest
    -0.34
    المكان
    -0.34
     thickly
    -0.34
    resizingMask
    -0.33
    POSITIVE LOGITS
    ⓘ
    0.77
    
    0.60
    Portail
    0.58
     surla
    0.58
    Hauptartikel
    0.52
    ScopeManager
    0.48
    WebVitals
    0.46
    Portale
    0.46
     StatelessWidget
    0.46
    WSGI
    0.45
    Activations Density 0.470%

    No Known Activations