© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6191
    Prev
    Next
    INDEX
    Explanations

    syntax related to decision-making and input handling in programming

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

    Code or math containing an equals sign

    np_acts-logits-general · gemini-2.0-flash

    asking for input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    )}_
    -0.54
    libur
    -0.51
     Kull
    -0.51
     ivelany
    -0.50
    ância
    -0.49
     AQUÍ
    -0.49
    inerja
    -0.48
     oprot
    -0.47
     Delivery
    -0.47
     censiti
    -0.47
    POSITIVE LOGITS
     input
    1.40
    input
    1.26
    Input
    1.09
     Input
    1.08
     prompt
    1.07
     inputs
    1.03
    prompt
    1.02
    Prompt
    0.99
    输入
    0.98
     ask
    0.98
    Activations Density 0.168%

    No Known Activations