© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3443
    Prev
    Next
    INDEX
    Explanations

    references to mathematical sets and their related operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical terminology related to sets and data analysis.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.54
    MethodManager
    -0.50
    Życiorys
    -0.49
    WritableDatabase
    -0.46
    Importante
    -0.44
    locu
    -0.44
     Browne
    -0.43
    Autowired
    -0.43
     Вікіпе
    -0.42
     ویکی‌پدی
    -0.42
    POSITIVE LOGITS
     set
    1.10
    set
    1.09
    Set
    1.05
     Set
    1.03
     SET
    0.84
    SET
    0.82
     sets
    0.81
    TypedDataSet
    0.80
     Sets
    0.79
    Sets
    0.78
    Activations Density 0.082%

    No Known Activations