© 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. 41-GEMMASCOPE-RES-16K
    11. 6981
    Prev
    Next
    INDEX
    Explanations

    terms related to errors and specific coding-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.62
     للاسماء
    -0.56
     незавершена
    -0.54
     оригіналу
    -0.52
    fjspx
    -0.49
    ésult
    -0.48
    áska
    -0.46
     ivelany
    -0.46
    oa̍t
    -0.45
     المعيارى
    -0.44
    POSITIVE LOGITS
    ć
    0.50
     się
    0.47
    Gön
    0.45
    jąc
    0.43
    my
    0.42
    łby
    0.41
    łożyć
    0.40
    cie
    0.39
     Öffentlichkeit
    0.39
     gustaría
    0.39
    Activations Density 0.065%

    No Known Activations