© 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. 9826
    Prev
    Next
    INDEX
    Explanations

    specific formatting or structure elements related to document type or references

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

    Code, markup, or lists

    np_acts-logits-general · gemini-2.0-flash

    separators before code/data elements

    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
    AsUp
    -0.47
     endregion
    -0.46
    initializeApp
    -0.45
     strick
    -0.45
    oa̍t
    -0.43
    Kne
    -0.43
    $__
    -0.42
     !”
    -0.41
    HasKey
    -0.41
     lit
    -0.41
    POSITIVE LOGITS
     AssemblyCulture
    0.84
     مرئيه
    0.76
     estimés
    0.76
    prefixer
    0.72
     JADX
    0.70
    tvguidetime
    0.67
    CloseOperation
    0.64
     ویکی‌پدیا
    0.64
    Билгалдахарш
    0.62
     Wicidata
    0.61
    Activations Density 0.457%

    No Known Activations