© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5499
    Prev
    Next
    INDEX
    Explanations

    terms related to data processing and database management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "ark" suffix, often related to villains/organizations

    np_acts-logits-general · gemini-2.0-flash

    Jark Matter, Don Armage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </table>
    -0.57
    |<\
    -0.54
    #>
    -0.53
     Quo
    -0.53
    :<
    -0.53
    "}")
    -0.52
    Tó
    -0.52
    )}^{
    -0.52
     Bagdad
    -0.51
    googleapis
    -0.50
    POSITIVE LOGITS
     ร์
    0.57
     oreille
    0.54
     RouterModule
    0.53
     désert
    0.52
    rer
    0.52
     borboleta
    0.51
     tvrd
    0.50
     prêtre
    0.50
     dureza
    0.50
     époux
    0.50
    Activations Density 2.279%

    No Known Activations