© 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-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 5069
    Prev
    Next
    INDEX
    Explanations

    fragments of code or programming language syntax related to function declarations and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 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
     propOrder
    -0.78
    הערות
    -0.68
    ंदीखरीदारी
    -0.67
    verifyException
    -0.63
    FormTagHelper
    -0.61
    timewa
    -0.60
    wist
    -0.59
     ddelweddau
    -0.58
    Bism
    -0.58
    berus
    -0.58
    POSITIVE LOGITS
    UnusedPrivate
    0.46
    uegos
    0.42
     astore
    0.42
    ViewImports
    0.41
    SpringBootTest
    0.41
    ParseTree
    0.41
    ra
    0.41
    extendable
    0.40
    UserScript
    0.40
    PreAuthorize
    0.40
    Activations Density 1.058%

    No Known Activations