© 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. 21-GEMMASCOPE-RES-16K
    11. 11825
    Prev
    Next
    INDEX
    Explanations

    references to unique, handcrafted products and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -1.11
    RefNanny
    -0.68
     initComponents
    -0.67
    WebElementEntity
    -0.67
    AddTagHelper
    -0.65
    IsContent
    -0.65
     ModelExpression
    -0.64
    parsedMessage
    -0.63
    IContainer
    -0.61
    ThroughAttribute
    -0.61
    POSITIVE LOGITS
     unique
    2.57
    unique
    2.26
    Unique
    2.05
     Unique
    2.04
     uniqueness
    1.96
     UNIQUE
    1.94
     uniques
    1.76
     unieke
    1.75
     uniquely
    1.73
    UNIQUE
    1.72
    Activations Density 0.192%

    No Known Activations