© 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. 22-GEMMASCOPE-RES-16K
    11. 1324
    Prev
    Next
    INDEX
    Explanations

    connections related to service and functions in programming context

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

    Characters immediately preceding certain suffixes

    np_acts-logits-general · gemini-2.0-flash

    various, VPN's, or code mappings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UpInside
    -0.56
    TagHelper
    -0.52
    참고
    -0.50
     CGRect
    -0.49
    fecture
    -0.49
    tabular
    -0.49
    TargetApi
    -0.48
     WebDriverWait
    -0.48
    cshtml
    -0.47
    Vorlage
    -0.46
    POSITIVE LOGITS
     getItemId
    0.76
    ideo
    0.61
     Anfitrión
    0.55
    igil
    0.52
    IsContent
    0.52
     Baillargeon
    0.52
    buttonBar
    0.49
    IEW
    0.48
     alue
    0.48
     Профиль
    0.48
    Activations Density 0.154%

    No Known Activations