© 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. 11663
    Prev
    Next
    INDEX
    Explanations

    technical terms related to furniture assembly and design

    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
    uniform
    -0.41
    Universe
    -0.40
     Universe
    -0.40
    enumii
    -0.40
    Uniform
    -0.39
     IActionResult
    -0.39
     uniform
    -0.36
    Unity
    -0.36
     seragam
    -0.35
    universe
    -0.35
    POSITIVE LOGITS
     U
    2.88
     u
    2.23
    U
    2.09
     у
    1.37
    u
    1.19
    Ｕ
    1.06
     У
    0.99
     उ
    0.97
    ｕ
    0.79
    У
    0.74
    Activations Density 0.589%

    No Known Activations