© 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. 6494
    Prev
    Next
    INDEX
    Explanations

    references to coding structures and programming language syntax

    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
    ScopeManager
    -0.51
     MainAxisSize
    -0.50
    PreInfinity
    -0.50
     дописавши
    -0.45
    çage
    -0.44
    ComponentModel
    -0.43
     SIMBAD
    -0.43
    ubov
    -0.43
    HtmlAttribute
    -0.42
    sizeCache
    -0.42
    POSITIVE LOGITS
     path
    1.59
    path
    1.38
     Path
    1.19
    Path
    1.16
    路径
    1.14
     PATH
    1.05
    PATH
    1.04
     paths
    0.97
     location
    0.93
     путь
    0.90
    Activations Density 0.636%

    No Known Activations