© 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. 31-GEMMASCOPE-RES-16K
    11. 7147
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to environmental treaties and climate change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases and concepts related to climate change and environmental policy solutions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Manip
    -0.43
     дописавши
    -0.41
     AssemblyVersion
    -0.41
     Manipulation
    -0.37
     بيها
    -0.37
    ImageContext
    -0.37
    toHexString
    -0.36
    msgTypes
    -0.36
    __":
    -0.35
     chromat
    -0.35
    POSITIVE LOGITS
     adaptation
    0.90
     Adaptation
    0.88
     flood
    0.85
    Adaptation
    0.81
     vulnerability
    0.79
     adaptación
    0.79
    adaptation
    0.78
     Vulnerability
    0.74
    flood
    0.71
     Anpass
    0.71
    Activations Density 0.198%

    No Known Activations