© 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. 39-GEMMASCOPE-RES-16K
    11. 4201
    Prev
    Next
    INDEX
    Explanations

    programming-related code constructs and database querying elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.52
    PageRoute
    -0.49
    WebVitals
    -0.48
    +#+#
    -0.47
    yntaxException
    -0.45
    IntoConstraints
    -0.45
     butterknife
    -0.44
    StoreMessageInfo
    -0.43
    +:+
    -0.43
    expandindo
    -0.42
    POSITIVE LOGITS
     dropdown
    1.24
     drop
    1.13
    dropdown
    1.08
     Dropdown
    1.06
     Drop
    1.05
    Dropdown
    1.02
    DropDown
    1.01
    下拉
    1.01
     select
    0.95
     choices
    0.91
    Activations Density 0.292%

    No Known Activations