© 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. 27-GEMMASCOPE-RES-16K
    11. 10351
    Prev
    Next
    INDEX
    Explanations

    phrases related to energy consumption and control

    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
     purpose
    -0.36
    jskiej
    -0.36
     habr
    -0.36
    годи
    -0.35
     가
    -0.35
    iph
    -0.35
    INTENANCE
    -0.35
    数料
    -0.33
    飽
    -0.33
    目的
    -0.33
    POSITIVE LOGITS
     uncontrollable
    1.09
     controllable
    1.08
     control
    1.08
    control
    0.99
     CONTROL
    0.98
     Control
    0.94
     controle
    0.94
     contrôle
    0.89
     kontrol
    0.87
    控制
    0.85
    Activations Density 0.288%

    No Known Activations