© 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. 35-GEMMASCOPE-RES-16K
    11. 9246
    Prev
    Next
    INDEX
    Explanations

    phrases expressing wishes or desires for change or improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oldukça
    -0.63
     quase
    -0.60
     remarkably
    -0.58
     nahezu
    -0.55
     vieles
    -0.54
     весьма
    -0.54
     практически
    -0.54
     aparentemente
    -0.54
     almost
    -0.53
     почти
    -0.53
    POSITIVE LOGITS
     autorytatywna
    1.03
     preferably
    0.84
    もう少し
    0.83
    preferably
    0.81
    もっと
    0.79
     someday
    0.79
     wenigstens
    0.79
     endlich
    0.78
     somehow
    0.77
    ंदीखरीदारी
    0.76
    Activations Density 1.139%

    No Known Activations