© 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. 8620
    Prev
    Next
    INDEX
    Explanations

    terms related to data collection and analysis of user interactions

    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
     MainAxisSize
    -0.64
    InSection
    -0.57
     offline
    -0.50
     GenerationType
    -0.50
     tongs
    -0.48
     AudioClip
    -0.48
    ốn
    -0.48
    makeConstraints
    -0.48
    CodeAttribute
    -0.47
     Sticks
    -0.47
    POSITIVE LOGITS
    WebElementEntity
    0.64
    forRoot
    0.60
    :✨
    0.54
     للاسماء
    0.54
    KURZBESCHREIBUNG
    0.51
    rxjs
    0.49
    abrigo
    0.47
    defineProperty
    0.47
    qvarna
    0.47
     kea
    0.46
    Activations Density 1.716%

    No Known Activations