© 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. 1-GEMMASCOPE-RES-16K
    11. 7931
    Prev
    Next
    INDEX
    Explanations

    elements related to data or object structures, particularly in the context of programming or API requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoreMessageInfo
    -0.56
    CGFloat
    -0.42
     WebDriverWait
    -0.42
    shadowOpacity
    -0.41
     FormData
    -0.40
     CGFloat
    -0.39
    respectively
    -0.39
    EndContext
    -0.39
     Klo
    -0.38
     Harg
    -0.37
    POSITIVE LOGITS
    []
    0.79
     AssemblyCulture
    0.69
    []
    0.67
     afield
    0.62
     chains
    0.58
    parsedMessage
    0.57
    []=
    0.55
    Container
    0.54
     betweenstory
    0.54
     Efq
    0.54
    Activations Density 0.200%

    No Known Activations