© 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-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 31841
    Prev
    Next
    INDEX
    Explanations

    references to instructions or guidelines

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    instruction set

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    лерея
    -0.79
     Neve
    -0.79
    찮
    -0.73
    Cubit
    -0.70
    AsUp
    -0.68
     cheeks
    -0.68
     $("<
    -0.68
    posedge
    -0.67
     ALBUM
    -0.67
    assertEqual
    -0.67
    POSITIVE LOGITS
     instructions
    1.14
     Instructions
    0.94
     instruction
    0.92
     INSTRUCTION
    0.88
    Instructions
    0.85
    instructions
    0.84
    Instru
    0.82
     Instruction
    0.81
    Instruction
    0.81
     instructed
    0.80
    Activations Density 0.017%

    No Known Activations