© 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. 18-GEMMASCOPE-RES-16K
    11. 10794
    Prev
    Next
    INDEX
    Explanations

    function calls and method definitions in programming code

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

    Java UI button "set" methods

    np_acts-logits-general · gemini-2.0-flash

    setting object properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ly
    -0.57
    s
    -0.55
    styleable
    -0.50
    afficheront
    -0.49
    an
    -0.48
     natin
    -0.47
    ArrowToggle
    -0.47
     while
    -0.47
     to
    -0.47
     Schro
    -0.47
    POSITIVE LOGITS
     Chwiliwch
    0.74
    NameInMap
    0.73
    SourceChecksum
    0.73
     CreateTagHelper
    0.73
     prêtres
    0.73
    Portale
    0.70
    :✨
    0.67
    enumi
    0.66
    inghouse
    0.66
    enance
    0.65
    Activations Density 0.050%

    No Known Activations