© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 14148
    Prev
    Next
    INDEX
    Explanations

    verbs related to raising or increasing something, particularly in a social or familial context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.91
     CURIAM
    -0.80
    ürtel
    -0.80
    достатки
    -0.69
    onov
    -0.66
     AssemblyCulture
    -0.65
    interopRequire
    -0.64
     OTHERWISE
    -0.64
    anovich
    -0.63
    continent
    -0.63
    POSITIVE LOGITS
     raise
    3.14
     raised
    3.14
     raising
    2.99
     Raise
    2.95
     Raising
    2.89
     Raised
    2.87
     raises
    2.84
    raised
    2.82
    Raise
    2.74
    Raising
    2.73
    Activations Density 0.056%

    No Known Activations