© 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. 1906
    Prev
    Next
    INDEX
    Explanations

    references to awards and nominations in the performing arts

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

    Awards for excellence or best performance

    np_acts-logits-general · gemini-2.0-flash

    best award categories

    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
    tso
    -0.46
    rod
    -0.44
     now
    -0.42
     ttk
    -0.40
    ula
    -0.40
     Thieves
    -0.39
    ViewFeatures
    -0.38
    bav
    -0.38
    tav
    -0.38
    rauch
    -0.38
    POSITIVE LOGITS
     excellence
    0.83
    mybatisplus
    0.81
    Excellence
    0.80
    annica
    0.80
    Outstanding
    0.79
    outstanding
    0.77
    ".
    0.76
    ."</
    0.75
    posób
    0.75
     exceptionnelle
    0.75
    Activations Density 0.103%

    No Known Activations