© 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. 12-GEMMASCOPE-RES-16K
    11. 6951
    Prev
    Next
    INDEX
    Explanations

    elements and attributes typically found in structured data formats like JSON or XML

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InstrumentedTest
    -0.76
    ernalia
    -0.72
    AsUp
    -0.71
    RectangleBorder
    -0.67
    IVEREF
    -0.65
    rawDesc
    -0.63
    webElement
    -0.63
    ModelForm
    -0.59
     '\\;'
    -0.57
    djangoproject
    -0.54
    POSITIVE LOGITS
    Hauptartikel
    0.73
     AssemblyTitle
    0.72
    ="@+
    0.64
     XCTest
    0.63
     مواليد
    0.62
     Efq
    0.60
    withIdentifier
    0.59
     houſe
    0.56
     CreateTagHelper
    0.55
    RCS
    0.53
    Activations Density 0.453%

    No Known Activations