© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 3751
    Prev
    Next
    INDEX
    Explanations

    specific roles or titles related to creators and operators in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addGap
    -0.69
    tableFuture
    -0.64
    AxisAlignment
    -0.54
    printStackTrace
    -0.52
     Мексичка
    -0.51
     EconPapers
    -0.51
    WriteAttribute
    -0.50
    ymce
    -0.50
    WriteLiteral
    -0.49
    numerusform
    -0.49
    POSITIVE LOGITS
    earcher
    0.84
     evaluator
    0.81
    evaluator
    0.80
     Seeker
    0.74
    tester
    0.74
     Remover
    0.73
    trainer
    0.72
    Creator
    0.71
     maker
    0.71
     scorer
    0.71
    Activations Density 0.852%

    No Known Activations