© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 12791
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental impacts and regulations

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

    words and phrases related to power plants, energy generation, and nuclear/coal infrastructure.

    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
    NameInMap
    -0.38
    esai
    -0.35
    faßt
    -0.35
    unteer
    -0.33
    zęd
    -0.33
    เสีย
    -0.33
    énario
    -0.32
     fallu
    -0.32
    నే
    -0.32
    ModelSerializer
    -0.32
    POSITIVE LOGITS
     power
    1.05
    power
    0.85
     Power
    0.85
     POWER
    0.82
    Power
    0.81
    発電
    0.78
     coal
    0.77
    POWER
    0.77
     Nuclear
    0.77
     turbine
    0.76
    Activations Density 0.169%

    No Known Activations