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

    Neuronpedia

    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 - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 9433
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relative comparisons or relationships between different entities or variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tartalomajánló
    -0.63
     OCC
    -0.57
     Tiro
    -0.56
    clusal
    -0.56
     Änder
    -0.55
    éné
    -0.55
     PY
    -0.54
    Extinguishing
    -0.53
    扣
    -0.53
    ActionEvent
    -0.52
    POSITIVE LOGITS
     respectively
    2.17
    respectively
    1.98
     respectivement
    1.73
     respectivamente
    1.64
     particularly
    1.45
     notamment
    1.43
     Specifically
    1.42
    Specifically
    1.41
     Particularly
    1.38
     namely
    1.33
    Activations Density 0.217%

    No Known Activations