© 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. 9-GEMMASCOPE-RES-16K
    11. 11265
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation used in programming syntax, particularly in Swift

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portale
    -0.63
    ACHUSET
    -0.59
     vectorielle
    -0.58
    GeoNames
    -0.49
     valentín
    -0.49
     betweenstory
    -0.49
    uttgart
    -0.48
     Normdatei
    -0.47
    ISupport
    -0.46
     "..\..\
    -0.46
    POSITIVE LOGITS
    unwrap
    0.62
    requireNonNull
    0.58
    orElseThrow
    0.54
    findOrFail
    0.53
    nativeElement
    0.50
    !
    0.48
    interopRequire
    0.48
    rawValue
    0.47
    ()?;
    0.47
    CurrentValue
    0.46
    Activations Density 0.200%

    No Known Activations