© 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-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 5934
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to mathematical or statistical computations involving relationships and numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     חיצוניים
    -0.54
     tartalomajánló
    -0.46
    ViewFeatures
    -0.46
    InjectAttribute
    -0.41
    alló
    -0.41
    LoadScene
    -0.41
    idorm
    -0.40
     vecka
    -0.39
     cesse
    -0.39
    RTSC
    -0.39
    POSITIVE LOGITS
     elements
    0.73
     pixels
    0.68
     possible
    0.68
     nodes
    0.66
     distinct
    0.66
     items
    0.65
     cells
    0.64
     consecutive
    0.63
     vertices
    0.62
     occurrences
    0.61
    Activations Density 2.269%

    No Known Activations