© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10088
    Prev
    Next
    INDEX
    Explanations

    structures and syntax associated with coding environments or programming languages

    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
    principalColumn
    -0.90
    InjectAttribute
    -0.81
     Normdatei
    -0.79
     Autorizaciones
    -0.77
    tagHelperRunner
    -0.76
     MainAxisSize
    -0.75
     JpaRepository
    -0.74
     utafitiHapana
    -0.69
    parsedMessage
    -0.68
    transQ
    -0.67
    POSITIVE LOGITS
    Begin
    0.49
     begun
    0.49
     new
    0.49
    mtable
    0.48
    BEGIN
    0.47
     Begin
    0.44
     started
    0.43
     a
    0.43
     begin
    0.43
     B
    0.42
    Activations Density 0.097%

    No Known Activations