© 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. 11-GEMMASCOPE-RES-16K
    11. 5030
    Prev
    Next
    INDEX
    Explanations

    occurrences of functions and methods related to size and length

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUrlHelper
    -0.53
     gynhyrchwyd
    -0.50
    adaptiveStyles
    -0.49
    mapStateToProps
    -0.43
     queſta
    -0.41
     JAXBElement
    -0.41
    -------
    -0.41
     '\\;'
    -0.41
     NavController
    -0.41
     userEmail
    -0.41
    POSITIVE LOGITS
    length
    0.88
    size
    0.84
     size
    0.81
     length
    0.79
    Length
    0.70
    Size
    0.67
     Length
    0.66
    LENGTH
    0.66
     Size
    0.65
    SIZE
    0.62
    Activations Density 0.228%

    No Known Activations