© 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. 1062
    Prev
    Next
    INDEX
    Explanations

    terms related to errors or exceptions in programming

    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
     Diri
    -0.55
     Basso
    -0.52
    fines
    -0.51
    ρί
    -0.47
    árna
    -0.47
    ítulos
    -0.46
     Kriminal
    -0.46
    Formatter
    -0.46
     BROTHERS
    -0.46
    topbar
    -0.46
    POSITIVE LOGITS
    MigrationBuilder
    1.07
    __*/
    0.86
    WriteLiteral
    0.75
    GEBURTSDATUM
    0.71
     AssemblyProduct
    0.71
     AssemblyTitle
    0.69
    IsMutable
    0.69
    IContainer
    0.67
     <<<<<<<<<<<<<<
    0.67
     الحره
    0.67
    Activations Density 0.077%

    No Known Activations