© 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 EvalsExportsinterp-engineNEWAPI 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. 6131
    Prev
    Next
    INDEX
    Explanations

    adjectives and their comparative forms describing quality or condition

    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
     Bare
    -0.36
    下载附件
    -0.36
     closest
    -0.35
     otomatig
    -0.35
    Char
    -0.33
     Not
    -0.32
     Char
    -0.32
    Ella
    -0.32
    Bab
    -0.31
     Ella
    -0.31
    POSITIVE LOGITS
     hơn
    1.01
    กว่า
    0.74
    ‌تر
    0.73
    lier
    0.71
    تر
    0.69
     تر
    0.68
    er
    0.67
     יותר
    0.67
    ebb
    0.65
     enough
    0.63
    Activations Density 0.205%

    No Known Activations