© 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. 14760
    Prev
    Next
    INDEX
    Explanations

    programming structures related to function calls and control flow

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

    Code snippets with parentheses and error handling

    np_acts-logits-general · gemini-2.0-flash

    closing parentheses in code

    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
     &___
    -0.57
     triển
    -0.56
     throw
    -0.53
    ModelAttribute
    -0.48
     throwing
    -0.47
     throws
    -0.46
    biet
    -0.45
    Hare
    -0.45
    貝
    -0.45
    läge
    -0.44
    POSITIVE LOGITS
    Espèce
    0.84
    ConstraintMaker
    0.82
     للاسماء
    0.74
     ويكيميديا
    0.67
    ftagPool
    0.66
    Referencer
    0.66
    queryInterface
    0.66
     发表于
    0.65
    adaptiveStyles
    0.64
    BagLayout
    0.64
    Activations Density 0.059%

    No Known Activations