© 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-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 57755
    Prev
    Next
    INDEX
    Explanations

    occurrences of the opening parentheses character in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TestingModule
    -0.80
     itſelf
    -0.76
    horizontalLayout
    -0.63
    ſelves
    -0.62
    UnusedPrivate
    -0.62
    neſs
    -0.59
     doInBackground
    -0.59
     Мексичка
    -0.58
    CodedInputStream
    -0.58
    AntiForgeryToken
    -0.57
    POSITIVE LOGITS
     Beyer
    0.56
     $=
    0.55
    PropertyChanged
    0.52
    ={<
    0.51
    \}=
    0.51
    rila
    0.50
    一是
    0.50
    زش
    0.50
    &=
    0.50
    }{*}{
    0.50
    Activations Density 0.009%

    No Known Activations