© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 7339
    Prev
    Next
    INDEX
    Explanations

    references to "new" or newly introduced concepts, features, or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RemindMe
    -0.57
    enderror
    -0.56
    extAlignment
    -0.55
    ffet
    -0.52
    +:+
    -0.52
     eventId
    -0.51
     Winaray
    -0.50
     BorderSide
    -0.50
    aneity
    -0.49
     Forumite
    -0.49
    POSITIVE LOGITS
     new
    1.57
    new
    1.33
     neuen
    1.20
     New
    1.18
     nueva
    1.17
    New
    1.16
     nuevos
    1.15
     nuevas
    1.14
     NEW
    1.14
     nuevo
    1.14
    Activations Density 0.073%

    No Known Activations