© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 598
    Prev
    Next
    INDEX
    Explanations

    elements related to health, wellness, and nutrition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mußten
    -0.50
    saraba
    -0.50
    harapkan
    -0.46
     Schönheit
    -0.45
    devamını
    -0.45
     preocupes
    -0.41
    ("")]
    -0.41
     dziew
    -0.41
     yarat
    -0.40
     mußte
    -0.40
    POSITIVE LOGITS
     equipments
    0.74
     stuffs
    0.72
     softwares
    0.61
     activities
    0.60
     thingy
    0.57
     purposes
    0.53
     personnels
    0.53
     songs
    0.52
     usages
    0.52
    MessageOf
    0.52
    Activations Density 0.723%

    No Known Activations