© 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 - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 12930
    Prev
    Next
    INDEX
    Explanations

    code related to the display of toast messages in Android applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.63
    Datuak
    -0.52
    WebElementEntity
    -0.49
    Swal
    -0.48
     sonata
    -0.47
     melo
    -0.46
     pire
    -0.46
     plau
    -0.46
    AddTagHelper
    -0.45
     FormsModule
    -0.45
    POSITIVE LOGITS
    Toast
    0.56
     Toast
    0.56
     durée
    0.51
     toast
    0.47
     indépendante
    0.47
    makeText
    0.46
     krótk
    0.46
    toast
    0.45
     toasted
    0.45
     Panjang
    0.44
    Activations Density 0.004%

    No Known Activations