© 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. 12411
    Prev
    Next
    INDEX
    Explanations

    patterns of punctuation and spacing in the text

    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
     Whilst
    -1.08
    Whilst
    -1.02
    非常的
    -0.95
     whilst
    -0.91
     however
    -0.78
     אשר
    -0.73
    慢慢的
    -0.73
     definately
    -0.72
    不断的
    -0.72
     Firstly
    -0.71
    POSITIVE LOGITS
     autorytatywna
    0.68
    Autoritní
    0.62
    こうした
    0.59
    onViewCreated
    0.58
     Ditto
    0.58
     staffers
    0.57
    Says
    0.56
    ◗
    0.56
     continúas
    0.56
    とはいえ
    0.55
    Activations Density 0.476%

    No Known Activations