© 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. 34-GEMMASCOPE-RES-16K
    11. 4985
    Prev
    Next
    INDEX
    Explanations

    specific technical instructions, configurations, and problem-solving elements related to software implementation and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recevrez
    -0.39
     varit
    -0.30
     Nuestros
    -0.28
     Мексичка
    -0.28
     quegli
    -0.28
     pesar
    -0.28
     касается
    -0.27
     tellement
    -0.27
    inSlope
    -0.27
     казалось
    -0.27
    POSITIVE LOGITS
     please
    1.52
     hãy
    1.47
     try
    1.30
    please
    1.28
     Please
    1.10
     PLEASE
    1.09
     consider
    1.08
     Try
    1.05
    请
    1.05
    Please
    1.04
    Activations Density 0.778%

    No Known Activations