Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15199
    Prev
    Next
    INDEX
    Explanations

    occurrences of the character '的' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    มี
    -0.89
    小
    -0.86
    方法
    -0.82
    问题
    -0.82
    故事
    -0.81
    大
    -0.80
    光
    -0.79
    原因
    -0.79
    时间
    -0.78
    มีความ
    -0.77
    POSITIVE LOGITS
     Мексичка
    0.85
    Personensuche
    0.85
    parsedMessage
    0.75
    Geplaatst
    0.73
    sidemargin
    0.72
     esboço
    0.71
    SBATCH
    0.70
     '\\;'
    0.68
    setVerticalGroup
    0.67
     esternos
    0.65
    Activations Density 0.127%

    No Known Activations