© 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. 3394
    Prev
    Next
    INDEX
    Explanations

    references to XML schemas and various attributes within code or configuration files

    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
    луй
    -0.50
     Lois
    -0.49
     resourceCulture
    -0.48
     nélkül
    -0.48
     strana
    -0.47
    नि
    -0.46
     Parma
    -0.46
    :][
    -0.45
    $}}
    -0.44
    Lois
    -0.44
    POSITIVE LOGITS
    AddTagHelper
    2.12
    ViewImports
    1.61
    InputTagHelper
    1.58
    ParallelGroup
    1.49
     lombok
    1.31
    AddHtmlAttribute
    1.27
    ########.
    1.07
    RenderAtEndOf
    1.04
    SpringBootTest
    1.03
    VersionUID
    1.01
    Activations Density 0.013%

    No Known Activations