© 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. 2-GEMMASCOPE-RES-16K
    11. 9415
    Prev
    Next
    INDEX
    Explanations

    words that convey positive attributes or experiences related to activities or content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cyfarwyddwr
    -0.55
     Jefus
    -0.54
     pleaſure
    -0.54
     houſe
    -0.52
     Majefty
    -0.51
     Reſ
    -0.49
     Houſe
    -0.49
    GEBURTSDATUM
    -0.47
    TagMode
    -0.47
    Recur
    -0.47
    POSITIVE LOGITS
     rewarding
    1.84
     engaging
    1.81
     appealing
    1.75
     inviting
    1.68
     encouraging
    1.66
     satisfying
    1.63
     inspiring
    1.59
     stimulating
    1.55
     promising
    1.52
     enticing
    1.51
    Activations Density 0.270%

    No Known Activations