© 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. 18-GEMMASCOPE-RES-16K
    11. 10015
    Prev
    Next
    INDEX
    Explanations

    programming functions and their parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code related to chart layout and boxes

    np_acts-logits-general · gemini-2.0-flash

    JSDoc comments and javascript methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nullptr
    -0.67
     $"{
    -0.61
    dataclass
    -0.59
    <>());
    -0.58
    ($"{
    -0.55
    nullptr
    -0.53
     restTemplate
    -0.53
     noexcept
    -0.51
    <>();
    -0.51
    <>(
    -0.51
    POSITIVE LOGITS
     Unders
    0.82
    WebControls
    0.80
     jQuery
    0.74
     Lightboxes
    0.73
    ngdoc
    0.73
    المكان
    0.71
     Umbra
    0.70
     Iroquois
    0.70
     = 
    0.69
     propOrder
    0.69
    Activations Density 0.940%

    No Known Activations