© 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. 16130
    Prev
    Next
    INDEX
    Explanations

    references to instance variables and method calls in programming code

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

    "this" followed by a period

    np_acts-logits-general · gemini-2.0-flash

    this in code constructors

    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
     [](
    -0.59
     Meksiku
    -0.58
     enää
    -0.54
    Transkript
    -0.53
     elástica
    -0.53
     Hopf
    -0.53
     ((*
    -0.50
    kegaard
    -0.49
     Stellung
    -0.49
    )";
    -0.49
    POSITIVE LOGITS
     Réponses
    0.75
    falen
    0.57
    انجليز
    0.56
    UnusedPrivate
    0.54
    PageRoute
    0.53
    通販
    0.53
    ViewFeatures
    0.52
    GenerationType
    0.52
    WebElementEntity
    0.52
    SequentialGroup
    0.51
    Activations Density 0.019%

    No Known Activations