© 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. 16348
    Prev
    Next
    INDEX
    Explanations

    expressions and functions related to programming or coding contexts

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

    Code related to UI elements or data structures

    np_acts-logits-general · gemini-2.0-flash

    installer, visitor, coder, adapter, crash

    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
    Hochspringen
    -0.73
     convaincre
    -0.72
    MemoryWarning
    -0.70
     défendre
    -0.68
     prouver
    -0.62
     détruire
    -0.61
     décrire
    -0.59
     peindre
    -0.58
     résoudre
    -0.56
     prévoir
    -0.56
    POSITIVE LOGITS
    getWriter
    0.81
    ers
    0.80
    ender
    0.78
    umenter
    0.75
     payer
    0.74
    lexer
    0.74
    adder
    0.73
    ander
    0.73
    siger
    0.72
    verifier
    0.72
    Activations Density 0.367%

    No Known Activations