© 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. 16-GEMMASCOPE-RES-16K
    11. 15378
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and structures related to creating, updating, and handling responses in API requests

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

    Error handling and return statements in Go code

    np_acts-logits-general · gemini-2.0-flash

    if err return

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (;;
    -0.61
    interopRequire
    -0.57
    {{/
    -0.50
     class
    -0.47
     onPostExecute
    -0.47
    ixote
    -0.46
     Pech
    -0.46
    sillo
    -0.46
    </tfoot>
    -0.46
     Al
    -0.46
    POSITIVE LOGITS
    sizeCache
    0.80
     ProtoMessage
    0.74
     protoimpl
    0.73
     autorytatywna
    0.71
    IUrlHelper
    0.71
     Bourgoin
    0.67
     disambiguazione
    0.66
     ErrIntOverflow
    0.66
     purpoſe
    0.62
     ffilmiau
    0.61
    Activations Density 1.085%

    No Known Activations