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

    Neuronpedia

    Jacobian LensNEW
    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. 33-GEMMASCOPE-RES-16K
    11. 12638
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the importance of assurance and reliability

    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
     mungkin
    -0.68
     quizá
    -0.65
    mutlich
    -0.64
     kadang
    -0.63
     Probably
    -0.63
    probably
    -0.63
     شاید
    -0.62
     probably
    -0.62
     preferring
    -0.62
    apparently
    -0.61
    POSITIVE LOGITS
     properly
    0.83
     adequately
    0.80
     correctly
    0.73
     adequate
    0.66
     sufficiently
    0.65
     accurately
    0.62
     correctement
    0.61
     megfelelő
    0.61
    properly
    0.59
     stays
    0.59
    Activations Density 0.446%

    No Known Activations