© 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. 18-GEMMASCOPE-RES-16K
    11. 9002
    Prev
    Next
    INDEX
    Explanations

    technical terms and structures related to programming or coding

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

    Incrementing or indexing numbers

    np_acts-logits-general · gemini-2.0-flash

    numbering or incrementing counters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.51
    GOTREF
    -0.49
     salaire
    -0.48
     dalamnya
    -0.47
     समीक्षाओं
    -0.46
    صف
    -0.45
     Wikispecies
    -0.42
    userdetails
    -0.42
     litté
    -0.41
     diretto
    -0.41
    POSITIVE LOGITS
     numbering
    1.32
     numbered
    1.23
     counting
    1.16
     increment
    1.13
     counter
    1.13
    counter
    1.11
    (++
    1.11
    COUNTER
    1.09
    counting
    1.08
    Counter
    1.07
    Activations Density 0.468%

    No Known Activations