© 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. 13874
    Prev
    Next
    INDEX
    Explanations

    technical or code-related terms and elements related to programming or data structures

    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
    isContained
    -0.83
     AssemblyVersion
    -0.71
    LayoutConstraint
    -0.69
    webElement
    -0.66
    chise
    -0.65
    rrggbb
    -0.65
    setVerticalGroup
    -0.65
    Portály
    -0.64
    PerformLayout
    -0.64
    idom
    -0.63
    POSITIVE LOGITS
    вгения
    0.52
     pikir
    0.48
    లాలు
    0.48
     المثال
    0.47
     Himo
    0.47
     wijk
    0.46
    (;;)
    0.45
     At
    0.45
    wiście
    0.44
    tales
    0.43
    Activations Density 0.220%

    No Known Activations