© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 10440
    Prev
    Next
    INDEX
    Explanations

    technical components and mechanisms related to electrical devices and switches

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     BoxFit
    -0.48
     burners
    -0.38
    Shrink
    -0.37
     planific
    -0.36
     substr
    -0.35
     Ther
    -0.35
     Shrink
    -0.35
     navel
    -0.35
    databinding
    -0.35
     свер
    -0.34
    POSITIVE LOGITS
     mechanism
    1.01
     mécanisme
    0.99
     mecanismo
    0.96
     Mechanism
    0.91
    mechanism
    0.89
    Mechanism
    0.87
     actuated
    0.84
     mechanisms
    0.84
     lever
    0.83
     mekan
    0.79
    Activations Density 0.977%

    No Known Activations