© 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. 16-GEMMASCOPE-RES-16K
    11. 13285
    Prev
    Next
    INDEX
    Explanations

    instructions related to email formatting and etiquette

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "do not" or similar negation

    np_acts-logits-general · gemini-2.0-flash

    don't do anything too much

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Not in Any Lists

    No Comments

    Negative Logits
    følgelig
    -0.72
    numerusform
    -0.67
    MessageOf
    -0.63
     yym
    -0.61
    الإنجليزية
    -0.60
    MessageTagHelper
    -0.60
    anggil
    -0.59
    ۜ
    -0.57
    enial
    -0.56
    CodedInputStream
    -0.56
    POSITIVE LOGITS
     any
    0.80
     anything
    0.77
     terlalu
    0.74
     unnecessarily
    0.74
     unless
    0.74
     слишком
    0.70
     excessively
    0.68
    Any
    0.67
     too
    0.67
     ANY
    0.67
    Activations Density 0.345%

    No Known Activations