© 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. 10-GEMMASCOPE-RES-16K
    11. 11828
    Prev
    Next
    INDEX
    Explanations

    descriptions of products or experiences that are highly recommended or ideal for specific purposes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UserScript
    -0.53
    contentLoaded
    -0.53
     utafitiHapana
    -0.49
     <>",
    -0.41
     esternos
    -0.40
     BigNumberish
    -0.39
     irré
    -0.39
     télécommande
    -0.39
     Exacts
    -0.38
     fourrure
    -0.37
    POSITIVE LOGITS
     ideal
    0.69
     ideales
    0.67
    ideal
    0.67
     ideale
    0.66
     Ideal
    0.66
    Ideal
    0.66
     suitable
    0.56
     vhodné
    0.56
     appropriate
    0.53
    suitable
    0.53
    Activations Density 0.281%

    No Known Activations