© 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. 9268
    Prev
    Next
    INDEX
    Explanations

    references to components and parts of objects or systems

    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
     penguins
    -0.91
    )");
    -0.90
     doInBackground
    -0.89
    zzleHttp
    -0.88
     lagoons
    -0.87
     ExecuteAsync
    -0.85
     conifers
    -0.83
    CloseOperation
    -0.83
    ynchronously
    -0.83
     pigeons
    -0.81
    POSITIVE LOGITS
     parts
    2.68
    Parts
    2.46
     Parts
    2.36
    parts
    2.30
     PARTS
    2.30
    PARTS
    1.90
     partes
    1.61
     Teile
    1.57
     components
    1.24
     Teilen
    1.17
    Activations Density 0.089%

    No Known Activations