© 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. 36-GEMMASCOPE-RES-16K
    11. 12805
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence of statistics or significant counts related to events and demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.60
     purpoſe
    -0.50
     diſt
    -0.49
     pleaſure
    -0.48
     cauſe
    -0.48
     Reſ
    -0.48
     चीज़ों
    -0.47
     تانيه
    -0.46
     ſtre
    -0.46
     ſec
    -0.45
    POSITIVE LOGITS
     were
    1.15
     wer
    0.84
     Were
    0.81
     ware
    0.80
    wer
    0.79
     Wer
    0.74
    were
    0.74
    vere
    0.72
     vere
    0.70
    Were
    0.68
    Activations Density 0.326%

    No Known Activations