© 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. 8-GEMMASCOPE-RES-16K
    11. 4829
    Prev
    Next
    INDEX
    Explanations

    C++ and Java programming elements related to input/output operations and layout management

    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
    migrationBuilder
    -0.78
    xaml
    -0.75
    colgroup
    -0.57
     herum
    -0.56
     ProtoMessage
    -0.55
     f
    -0.55
    awtextra
    -0.54
     ")";
    -0.52
     Williamson
    -0.51
    жалуйста
    -0.51
    POSITIVE LOGITS
    dirname
    1.37
     dirname
    1.15
    databind
    0.93
    CrossRef
    0.80
    enumii
    0.72
    IUrlHelper
    0.70
    Архівовано
    0.69
    PreExecute
    0.69
    pyx
    0.69
     rêver
    0.68
    Activations Density 0.016%

    No Known Activations