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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 10833
    Prev
    Next
    INDEX
    Explanations

    code-related terms or placeholders in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.98
    DataAnnotations
    -0.89
    AxisAlignment
    -0.85
    UnknownFieldSet
    -0.83
    prepareStatement
    -0.82
    urlpatterns
    -0.82
     EdgeInsets
    -0.74
    AnchorStyles
    -0.73
    SpringBootTest
    -0.70
    TagHelper
    -0.68
    POSITIVE LOGITS
    InjectAttribute
    1.13
     stub
    0.70
    Bronnen
    0.68
     noqa
    0.66
     TestBed
    0.63
    Архівовано
    0.63
     Архів
    0.60
    CppMethod
    0.59
     insuffisamment
    0.58
     ujednoznacz
    0.53
    Activations Density 0.008%

    No Known Activations