© 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. 15-GEMMASCOPE-RES-16K
    11. 2934
    Prev
    Next
    INDEX
    Explanations

    references to quality and standards in products or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases that describe attributes of quality and excellence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexContent
    -0.65
    SequentialGroup
    -0.65
    $_['
    -0.60
    lami
    -0.53
    CardType
    -0.53
     hart
    -0.52
     Arrangement
    -0.49
    memberOf
    -0.49
     Scalars
    -0.48
    ígenes
    -0.48
    POSITIVE LOGITS
     quality
    1.69
    quality
    1.49
     QUALITY
    1.31
     Quality
    1.31
    Quality
    1.31
     kwaliteit
    1.29
    QUALITY
    1.21
     kvalitet
    1.13
     Qualität
    1.13
     qualité
    1.12
    Activations Density 0.267%

    No Known Activations