© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 2150
    Prev
    Next
    INDEX
    Explanations

    legal terms related to penalties, liabilities, and legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.59
    Erreferentziak
    -0.58
     celib
    -0.55
     trivi
    -0.54
     roommates
    -0.54
    majánló
    -0.52
     unpredic
    -0.52
     confound
    -0.50
     toothpaste
    -0.50
    solicited
    -0.49
    POSITIVE LOGITS
     ModelExpression
    0.46
     shall
    0.41
     ladite
    0.39
     hereinafter
    0.36
     skall
    0.35
    いわゆる
    0.34
     delgada
    0.34
     thereof
    0.34
     duly
    0.34
     impresión
    0.33
    Activations Density 0.971%

    No Known Activations