© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 819
    Prev
    Next
    INDEX
    Explanations

    occurrences of the programming command "get" and its related syntax elements

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

    Properties with getter and setter methods

    np_acts-logits-general · gemini-2.0-flash

    private set property definition

    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
    webElementXpaths
    -0.71
    :✨
    -0.66
    RegressionTest
    -0.60
     Eup
    -0.58
    LabelTagHelper
    -0.58
     Erfolgs
    -0.56
    buttonBar
    -0.55
    urlpatterns
    -0.54
    toMatchSnapshot
    -0.53
    Geografi
    -0.53
    POSITIVE LOGITS
     private
    0.82
    private
    0.74
     set
    0.71
    PRIVATE
    0.52
     protected
    0.52
     internal
    0.52
    uiente
    0.51
    set
    0.51
    XmlIgnore
    0.51
     privately
    0.49
    Activations Density 0.016%

    No Known Activations