© 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. 34-GEMMASCOPE-RES-16K
    11. 1909
    Prev
    Next
    INDEX
    Explanations

    words related to variability and change across different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lorette
    -0.58
     للمعارف
    -0.58
    rungsseite
    -0.56
     Larger
    -0.52
    Larger
    -0.48
     Taktlose
    -0.48
     Bigger
    -0.46
     CUCET
    -0.46
    كويكب
    -0.45
    Bigger
    -0.45
    POSITIVE LOGITS
     greatly
    2.03
     considerably
    1.77
     significantly
    1.75
     tremendously
    1.73
     immensely
    1.71
     enormously
    1.66
     substantially
    1.57
     drastically
    1.45
     markedly
    1.43
     heavily
    1.40
    Activations Density 1.140%

    No Known Activations