© 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-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 10443
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to measurements and properties in scientific contexts, particularly focusing on dimensions, variability, and resistance attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.82
    脚注の使い方
    -0.79
    httphttps
    -0.76
     Roskov
    -0.75
    󠁬
    -0.75
    afficheront
    -0.74
     queſta
    -0.74
    addCriterion
    -0.73
     оригіналу
    -0.73
    Rhestr
    -0.73
    POSITIVE LOGITS
     value
    0.47
    值
    0.45
     levels
    0.42
     level
    0.42
     values
    0.40
     tinggi
    0.40
     increase
    0.40
     calculated
    0.39
     ratio
    0.39
     score
    0.39
    Activations Density 2.018%

    No Known Activations