© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 14-GEMMASCOPE-RES-16K
    11. 14346
    Prev
    Next
    INDEX
    Explanations

    phrases that convey the existence or characteristics of certain subjects, often related to processes or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     alimentaire
    -0.72
     alimentaires
    -0.68
     varandra
    -0.63
     propOrder
    -0.63
    eraard
    -0.62
     mày
    -0.60
     préfé
    -0.59
    
    -0.57
     internationales
    -0.57
    AnchorTagHelper
    -0.56
    POSITIVE LOGITS
    sequelize
    0.65
    примеча
    0.65
     المعيارى
    0.65
    LEncoder
    0.64
    "]
    0.61
    tonsoft
    0.61
    makeText
    0.60
    Citiți
    0.59
    jdt
    0.59
    ?";
    0.59
    Activations Density 0.237%

    No Known Activations