© 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. 4-GEMMASCOPE-RES-16K
    11. 11762
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to analytics and data processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WEBPACK
    -0.64
    contentLoaded
    -0.60
    новниш
    -0.58
    WebVitals
    -0.56
     Connectez
    -0.55
     INTERESAR
    -0.54
    BeginContext
    -0.54
     desaf
    -0.54
    OwnProperty
    -0.54
     lohnt
    -0.54
    POSITIVE LOGITS
     eventdata
    0.52
    WebMethod
    0.48
    enci
    0.48
    ,:);
    0.47
     roof
    0.47
     Simpli
    0.47
     Roof
    0.46
     üzere
    0.46
    istoitu
    0.46
    roof
    0.46
    Activations Density 2.277%

    No Known Activations