© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5954
    Prev
    Next
    INDEX
    Explanations

    declarative and interrogative statements related to debugging in programming

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

    Code debugging and tracing

    np_acts-logits-general · gemini-2.0-flash

    use the debugger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cập
    -0.55
     Malo
    -0.54
    complexContent
    -0.54
    Obrázky
    -0.51
     nonatomic
    -0.51
    upol
    -0.51
    脚注の使い方
    -0.50
    GraphicsUnit
    -0.49
    الثة
    -0.47
    complexType
    -0.46
    POSITIVE LOGITS
     debugging
    1.37
     debug
    1.33
     Debug
    1.17
     Debugging
    1.17
     debugger
    1.10
    debug
    1.10
    Debugging
    1.03
     trace
    1.03
     debu
    1.03
    Debug
    1.02
    Activations Density 0.721%

    No Known Activations