© 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. 1-GEMMASCOPE-RES-16K
    11. 7648
    Prev
    Next
    INDEX
    Explanations

    punctuation, specifically apostrophes and single quotation marks in dialogue or contractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTLD
    -0.74
    ″]
    -0.64
    …’
    -0.63
    NamedQueries
    -0.63
     @"/
    -0.61
    SpringBootTest
    -0.60
    IUrlHelper
    -0.59
     betweenstory
    -0.59
    ?’
    -0.58
     comigo
    -0.57
    POSITIVE LOGITS
    ⓘ
    0.53
    原始内容存档于
    0.52
    selectAll
    0.48
    équilibre
    0.45
    որ
    0.44
    getOutputStream
    0.44
    stdlib
    0.44
    urlpatterns
    0.44
    \]
    0.44
     like
    0.42
    Activations Density 0.145%

    No Known Activations