© 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. 34-GEMMASCOPE-RES-16K
    11. 1698
    Prev
    Next
    INDEX
    Explanations

    references to buying, selling, and descriptions of used or second-hand items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zákaz
    -0.34
     medži
    -0.33
    KommentareTeilen
    -0.33
     applicazione
    -0.33
    centration
    -0.33
    Eksterne
    -0.33
     retenir
    -0.33
    êng
    -0.33
     موفق
    -0.32
     ventaja
    -0.32
    POSITIVE LOGITS
     used
    1.70
     secondhand
    1.59
     Used
    1.57
    Used
    1.55
    used
    1.50
     USED
    1.48
    USED
    1.34
    二手
    1.33
    中古
    1.30
     usado
    1.29
    Activations Density 0.184%

    No Known Activations