© 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. 133
    Prev
    Next
    INDEX
    Explanations

    elements and syntax related to programming and data processing, particularly in the context of queries, rewrites, and scheduled tasks

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

    "Rewrite" or "async" keywords

    np_acts-logits-general · gemini-2.0-flash

    rewrite rules

    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
     kasarigan
    -1.46
    ValueStyle
    -1.19
    rungsseite
    -1.09
     مرئيه
    -1.05
     كومونز
    -1.04
    fjspx
    -1.03
     autorytatywna
    -1.02
    ChildScrollView
    -1.02
     تانيه
    -1.01
    исленность
    -1.00
    POSITIVE LOGITS
    \<^
    0.54
     hutan
    0.46
    ſand
    0.45
    {}".
    0.45
    rstrip
    0.44
     föruts
    0.43
    éphane
    0.43
    toHaveBeenCalled
    0.43
    ſel
    0.43
     øns
    0.43
    Activations Density 0.251%

    No Known Activations