© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1736
    Prev
    Next
    INDEX
    Explanations

    the beginning of a document or section indicating a new topic or context switch

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

    terminating punctuation and operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.77
     nakalista
    -0.74
    Vidite
    -0.73
    ThroughAttribute
    -0.73
    WEBPACK
    -0.71
    RegistryLite
    -0.69
    GEBURTSDATUM
    -0.68
     CreateTagHelper
    -0.67
    Földrajzportál
    -0.67
    tvguidetime
    -0.67
    POSITIVE LOGITS
    <bos>
    0.64
    anmoins
    0.59
    Приятного
    0.59
    Conclusie
    0.57
     tartalomajánló
    0.56
     Además
    0.56
     Daarnaast
    0.56
     Inoltre
    0.52
    Важно
    0.51
    țională
    0.51
    Activations Density 0.707%

    No Known Activations