© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11765
    Prev
    Next
    INDEX
    Explanations

    the word 'instruction' and related terms in the context of computer architecture

    oai_token-act-pair · gemini-2.0-flash

    instruction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     instructions
    -2.53
     instruction
    -2.38
     Instructions
    -2.20
     Instruction
    -2.13
    instructions
    -2.09
    Instructions
    -2.00
    instruction
    -1.99
     INSTRUCTIONS
    -1.89
    Instruction
    -1.89
     INSTRUCTION
    -1.81
    POSITIVE LOGITS
    #+#
    0.90
     propOrder
    0.71
    protoimpl
    0.69
    Rujuakan
    0.63
     wireType
    0.61
    artifactId
    0.57
    multirow
    0.56
     محفوظة
    0.56
    jspx
    0.55
    inazione
    0.55
    Activations Density 1.775%

    No Known Activations