© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15079
    Prev
    Next
    INDEX
    Explanations

    components and structure within programming code, particularly in the context of Angular or React applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     mixtures
    -0.38
     mixture
    -0.36
    awtextra
    -0.33
     khúc
    -0.33
    concat
    -0.33
    kirakan
    -0.32
     mix
    -0.32
    ']));
    -0.32
     lấy
    -0.31
    taus
    -0.30
    POSITIVE LOGITS
     nahilalakip
    0.70
    expandindo
    0.63
    Tikang
    0.63
    ंदीखरीदारी
    0.60
    WebElementEntity
    0.60
     ujednoznacz
    0.58
    alakip
    0.57
    arangay
    0.57
     SwitchCompat
    0.57
    WebVitals
    0.55
    Activations Density 0.201%

    No Known Activations