© 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. 27-GEMMASCOPE-RES-16K
    11. 11619
    Prev
    Next
    INDEX
    Explanations

    technical specifications and procedures related to manufacturing or engineering processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    udahkan
    -0.46
     rospy
    -0.46
    HomeAsUpEnabled
    -0.43
    انتهای
    -0.42
     argparse
    -0.42
    SharedDtor
    -0.42
    Aiheesta
    -0.41
    setPointSize
    -0.40
    contentLoaded
    -0.38
    Hose
    -0.38
    POSITIVE LOGITS
     thickness
    1.23
     thicknesses
    1.13
     Thickness
    1.13
    thickness
    1.11
    Thickness
    1.09
    厚度
    0.98
     layers
    0.96
     layer
    0.91
     Layers
    0.89
    厚
    0.87
    Activations Density 1.004%

    No Known Activations