© 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. 14-GEMMASCOPE-RES-16K
    11. 2461
    Prev
    Next
    INDEX
    Explanations

    phrases related to removing or eliminating unwanted elements or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FetchType
    -0.54
    odiment
    -0.47
     lectured
    -0.45
    Fail
    -0.43
    󠁿
    -0.43
    titleMargin
    -0.42
    _{+}
    -0.41
     fail
    -0.41
     Fail
    -0.41
    ukseen
    -0.41
    POSITIVE LOGITS
     unwanted
    0.81
     elimin
    0.70
     eliminare
    0.65
    Elimin
    0.65
    UnusedPrivate
    0.65
     menghilangkan
    0.63
     fVar
    0.62
    Pyx
    0.62
    زالة
    0.62
    uskas
    0.61
    Activations Density 0.317%

    No Known Activations