© 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. 11-GEMMASCOPE-RES-16K
    11. 10930
    Prev
    Next
    INDEX
    Explanations

    specific terms related to insulin signaling and various components of vehicle electrical systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abetes
    -0.80
     AssemblyProduct
    -0.73
    MigrationBuilder
    -0.72
    onViewCreated
    -0.70
     transférez
    -0.69
    ijų
    -0.66
    AndEndTag
    -0.62
     HasFactory
    -0.62
    aarrggbb
    -0.61
    Портал
    -0.61
    POSITIVE LOGITS
     due
    0.49
     owing
    0.49
    DECREF
    0.47
    りが
    0.44
    due
    0.44
     debido
    0.43
     فق
    0.43
     mysteriously
    0.42
    を失
    0.42
     alas
    0.42
    Activations Density 0.592%

    No Known Activations