Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11751
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and expressions related to dimensions and matrices in a neural network context

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

    Mathematical notation related to dimensions/matrices

    np_acts-logits-general · gemini-2.0-flash

    dimensions and size

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    Limit
    -0.51
    PII
    -0.49
     %=
    -0.49
     Limit
    -0.46
    uto
    -0.44
    [:]
    -0.44
    ByType
    -0.44
     pár
    -0.43
    énario
    -0.43
    love
    -0.43
    POSITIVE LOGITS
     dimensions
    0.68
     MainAxisSize
    0.65
    LookAnd
    0.61
    Dimension
    0.60
     dimension
    0.60
     dimensionality
    0.59
     demen
    0.57
     numberOfRows
    0.56
     يتيمه
    0.53
    ChromeDriver
    0.53
    Activations Density 0.148%

    No Known Activations