© 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. 21-GEMMASCOPE-RES-16K
    11. 3816
    Prev
    Next
    INDEX
    Explanations

    terminology related to scientific advancements and improvements in technology

    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
    isempty
    -0.46
     isempty
    -0.42
     kereszt
    -0.42
    Aplic
    -0.42
    ้อน
    -0.41
    databinding
    -0.41
    nodata
    -0.40
    льтра
    -0.40
     distinguer
    -0.40
     assigns
    -0.40
    POSITIVE LOGITS
     improve
    2.26
     increase
    2.13
     improved
    2.09
    improve
    2.06
     improving
    2.03
     improves
    2.02
     improvement
    1.99
     Improve
    1.95
     enhance
    1.91
     increased
    1.91
    Activations Density 1.167%

    No Known Activations