© 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. 36-GEMMASCOPE-RES-16K
    11. 8332
    Prev
    Next
    INDEX
    Explanations

    references to technology and its impact on experiences

    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
    何况
    -0.54
     nuanced
    -0.49
     чтоб
    -0.46
    我没
    -0.44
    没人
    -0.44
    tfrac
    -0.44
     halved
    -0.44
    他能
    -0.42
    hless
    -0.42
     resists
    -0.41
    POSITIVE LOGITS
     quite
    0.90
    非常的
    0.90
     basically
    0.88
     ganske
    0.85
     actually
    0.85
     faktiskt
    0.84
     eigenlijk
    0.82
     absolutamente
    0.79
     réellement
    0.79
    quite
    0.78
    Activations Density 3.134%

    No Known Activations