© 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. 23-GEMMASCOPE-RES-16K
    11. 11424
    Prev
    Next
    INDEX
    Explanations

    references to mathematical or technical concepts related to combinatorial theory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ьаж
    -0.87
    tagHelperRunner
    -0.77
    RegistryLite
    -0.74
    OrBuilder
    -0.74
    ImageContext
    -0.66
    AndEndTag
    -0.65
    DockStyle
    -0.64
     "..\..\..\
    -0.61
     "..\..\
    -0.60
    Билгалдахарш
    -0.60
    POSITIVE LOGITS
     olev
    0.69
    された
    0.58
    된
    0.55
     した
    0.54
    readed
    0.53
    puted
    0.52
    した
    0.52
    шед
    0.51
     된
    0.51
    った
    0.50
    Activations Density 0.077%

    No Known Activations