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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1095
    Prev
    Next
    INDEX
    Explanations

    code related to database context and repository patterns in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.90
     ThemeData
    -0.77
    //});
    -0.71
    Дереккөздер
    -0.70
    WireFormatLite
    -0.64
    lings
    -0.64
    >");
    -0.64
    enius
    -0.64
     OFDb
    -0.62
    طلحات
    -0.62
    POSITIVE LOGITS
    abestanden
    0.81
     York
    0.52
     ujednoznacz
    0.51
    HTTPResponse
    0.45
     насељу
    0.44
    逃
    0.44
    炸
    0.43
    FXMLLoader
    0.43
     educativas
    0.42
    .*")]
    0.41
    Activations Density 0.134%

    No Known Activations