© 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. 6958
    Prev
    Next
    INDEX
    Explanations

    syntactical structures and identifiers typical in programming or mathematical expressions

    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
     فريبيس
    -1.19
    StructEnd
    -1.02
    хьтан
    -1.02
     otomatig
    -0.99
    XmlAccessType
    -0.98
     للمعارف
    -0.94
     صوتيه
    -0.89
    yntaxException
    -0.86
     AssemblyVersion
    -0.86
     vPvB
    -0.84
    POSITIVE LOGITS
    Hozzáférés
    0.63
    ())),
    0.51
    Искәрмәләр
    0.47
    stretchr
    0.47
    )))),
    0.46
    bitField
    0.45
    toolTip
    0.40
    Ծանոթ
    0.39
    。「
    0.39
    ✺
    0.38
    Activations Density 0.708%

    No Known Activations