© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 108774
    Prev
    Next
    INDEX
    Explanations

    references to text field components in programming

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

    text fields and delegates

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    !*\
    -0.68
    Parcelize
    -0.64
     Osorio
    -0.61
    onAttach
    -0.59
    Personensuche
    -0.59
     Rptr
    -0.58
     ILogger
    -0.56
    onOptions
    -0.56
    SBATCH
    -0.54
     lệ
    -0.54
    POSITIVE LOGITS
    TextField
    1.20
     TextField
    1.18
     textField
    0.81
    textField
    0.77
    textfield
    0.74
     JTextField
    0.61
     UITextField
    0.61
    JTextField
    0.57
    FieldNumber
    0.54
     TextFormField
    0.53
    Activations Density 0.001%

    No Known Activations