© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 4063
    Prev
    Next
    INDEX
    Explanations

    terms related to financial or legal misconduct

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     soldiers
    -0.94
     military
    -0.93
    Military
    -0.92
    military
    -0.90
    Army
    -0.89
     troops
    -0.88
     Army
    -0.86
     Military
    -0.86
     army
    -0.85
     soldier
    -0.84
    POSITIVE LOGITS
    MigrationBuilder
    0.79
     disambiguazione
    0.76
     betweenstory
    0.72
     DataTypes
    0.70
    rungsseite
    0.69
    principalTable
    0.68
    RuleContext
    0.62
    poons
    0.57
    YLON
    0.56
    runApp
    0.55
    Activations Density 3.081%

    No Known Activations