© 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. 5-GEMMASCOPE-RES-16K
    11. 15594
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and structural elements in programming or scripting languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zijne
    -0.55
    idik
    -0.51
     tibi
    -0.50
    pstead
    -0.49
     übrigens
    -0.49
     rojas
    -0.46
     Tiểu
    -0.45
     suaminya
    -0.45
    tive
    -0.45
    pgf
    -0.44
    POSITIVE LOGITS
    GEBURTSDATUM
    0.83
    findpost
    0.80
     ModelExpression
    0.78
    featureID
    0.75
    indd
    0.73
     initComponents
    0.71
     Signalez
    0.70
     unknownFields
    0.69
    ReusableCell
    0.68
     viewDidLoad
    0.68
    Activations Density 0.411%

    No Known Activations