© 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. 4-GEMMASCOPE-RES-16K
    11. 10320
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers related to genetic sequences and laboratory procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oader
    -0.51
    UnusedPrivate
    -0.47
     []:
    -0.46
    specifier
    -0.44
     Grand
    -0.42
     of
    -0.42
     CÁ
    -0.42
     Lead
    -0.42
     bị
    -0.41
     les
    -0.41
    POSITIVE LOGITS
    TintMode
    0.93
     cdti
    0.85
     pleaſure
    0.79
     AppModule
    0.77
    ItemBackground
    0.77
     CreateTagHelper
    0.75
     للمعارف
    0.73
     itſelf
    0.72
     tdci
    0.72
     berätt
    0.70
    Activations Density 1.879%

    No Known Activations