© 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-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 11938
    Prev
    Next
    INDEX
    Explanations

    organizational structures and formal entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sneaky
    -0.42
     OMITBAD
    -0.38
    WireFormatLite
    -0.37
    意外
    -0.37
    /***/
    -0.36
     ویکی‌پدی
    -0.36
     unexpected
    -0.35
     sufre
    -0.34
     puntual
    -0.34
    лю
    -0.34
    POSITIVE LOGITS
     organization
    0.72
    established
    0.72
     organisation
    0.70
     established
    0.70
     founded
    0.69
     establishment
    0.69
     gegründet
    0.69
     Established
    0.68
    founded
    0.68
    成立
    0.65
    Activations Density 0.798%

    No Known Activations