© 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. 2-GEMMASCOPE-RES-16K
    11. 4637
    Prev
    Next
    INDEX
    Explanations

    syntax-related elements and structures in code or programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Honour
    -0.55
     EnglishChoose
    -0.55
    Hochspringen
    -0.54
     roule
    -0.53
     roux
    -0.53
    netbeans
    -0.53
     onPostExecute
    -0.51
    IUrlHelper
    -0.48
     bursa
    -0.48
    ulatory
    -0.48
    POSITIVE LOGITS
    interopRequire
    0.88
    eseorang
    0.72
    endphp
    0.69
    brainly
    0.67
    /');
    0.67
     CreateTagHelper
    0.64
    PerformLayout
    0.62
    EndContext
    0.61
    //});
    0.60
    újo
    0.60
    Activations Density 1.003%

    No Known Activations