© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2212
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving negative powers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Driscoll
    -0.77
     Larkin
    -0.73
     McMillan
    -0.67
    ь
    -0.67
     anda
    -0.66
    udz
    -0.65
    tedt
    -0.65
     el
    -0.64
    ات
    -0.63
    laß
    -0.61
    POSITIVE LOGITS
     }^{-
    1.50
    ^{-
    1.48
    )^{-
    1.45
    ]^{-
    1.39
    }^{-
    1.37
     ^{-
    1.15
    ^{-\
    1.11
    NegativeButton
    0.98
     $[-
    0.97
     pleaſure
    0.96
    Activations Density 0.299%

    No Known Activations