© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 367
    Prev
    Next
    INDEX
    Explanations

    adverbs describing quality or manner, particularly focusing on those emphasizing carefulness or effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.77
    findpost
    -0.73
     للاسماء
    -0.72
     ostavi
    -0.65
    ViewFeatures
    -0.58
    Personensuche
    -0.57
     كومونز
    -0.55
     فريبيس
    -0.53
    TagMode
    -0.53
    KommentareTeilen
    -0.53
    POSITIVE LOGITS
     designed
    0.69
     executed
    0.67
     thought
    0.64
     presented
    0.61
     crafted
    0.60
     appointed
    0.59
     conceived
    0.59
     rendered
    0.58
     composed
    0.57
    designed
    0.57
    Activations Density 0.256%

    No Known Activations