© 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-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 7931
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "instruction" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nema
    -0.72
    thical
    -0.69
    SPATH
    -0.68
    mydb
    -0.68
    artifactId
    -0.66
    angliski
    -0.66
    ConstraintMaker
    -0.64
     mxArray
    -0.64
     parseFrom
    -0.63
    HKEY
    -0.63
    POSITIVE LOGITS
     instruction
    2.91
     Instruction
    2.76
     instructions
    2.69
    Instruction
    2.50
    instruction
    2.48
     Instructions
    2.47
     INSTRUCTION
    2.42
    instructions
    2.23
    Instructions
    2.18
     INSTRUCTIONS
    2.08
    Activations Density 0.050%

    No Known Activations