© 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. 2680
    Prev
    Next
    INDEX
    Explanations

    terms related to reductions or decreases in various contexts

    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
     ‘
    -0.79
    dür
    -0.70
    mobileqq
    -0.63
     C
    -0.63
    ’
    -0.60
     “
    -0.60
     G
    -0.60
    iVar
    -0.59
    G
    -0.56
    Portale
    -0.56
    POSITIVE LOGITS
     decrease
    2.12
     Decrease
    1.98
     decreases
    1.96
     decreasing
    1.93
    decrease
    1.88
    Decrease
    1.87
     decreased
    1.85
     Decre
    1.81
    Decre
    1.74
     Decreased
    1.73
    Activations Density 0.125%

    No Known Activations