© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 11168
    Prev
    Next
    INDEX
    Explanations

    phrases related to time duration and treatment processes in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.61
     חיצוניים
    -0.54
    BeginInit
    -0.45
     BoxDecoration
    -0.44
    Sucesor
    -0.43
     month
    -0.43
     måned
    -0.43
     годов
    -0.42
    个月
    -0.42
    TagHelper
    -0.42
    POSITIVE LOGITS
     hours
    0.94
     HOURS
    0.80
     Hours
    0.77
     horas
    0.75
    hours
    0.75
     сутки
    0.75
    Hours
    0.74
    二十四
    0.67
    HOURS
    0.66
     heures
    0.63
    Activations Density 0.358%

    No Known Activations