© 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. 5-GEMMASCOPE-RES-16K
    11. 7854
    Prev
    Next
    INDEX
    Explanations

    quotes or string literals in programming or scripting contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.73
     JpaRepository
    -0.58
    SqlDataReader
    -0.54
    makeatother
    -0.52
    antMatchers
    -0.52
    HasForeignKey
    -0.52
     /\.(
    -0.51
    slidesToShow
    -0.51
    slidesPer
    -0.51
    hatenablog
    -0.50
    POSITIVE LOGITS
    脚注の使い方
    0.65
    thâu
    0.64
    ыгана
    0.63
    WebVitals
    0.60
    ंदीखरीदारी
    0.59
    цездатний
    0.59
    ArrowToggle
    0.56
    mbic
    0.56
    InitVars
    0.56
    ScopeManager
    0.55
    Activations Density 0.115%

    No Known Activations