© 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. 15652
    Prev
    Next
    INDEX
    Explanations

    phrases that express an opinion or response to a statement

    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
    단
    -0.37
    いなかった
    -0.36
    Fornecedor
    -0.35
     Vessel
    -0.34
    Lazar
    -0.34
    Recipient
    -0.33
    PC
    -0.33
     recipient
    -0.33
    PM
    -0.33
     hodin
    -0.32
    POSITIVE LOGITS
    Sounds
    0.79
    sounds
    0.73
     sounds
    0.72
     sounded
    0.72
     Sounds
    0.69
     ModelExpression
    0.69
     klingt
    0.66
     suena
    0.64
     sounding
    0.59
    twimg
    0.57
    Activations Density 0.152%

    No Known Activations