© 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 - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 7056
    Prev
    Next
    INDEX
    Explanations

    references to "series," indicating the focus on collections or sequences of items or events

    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
    脚注の使い方
    -0.63
    })]
    -0.58
    cshtml
    -0.57
    Šaltiniai
    -0.57
     sappi
    -0.56
    ufig
    -0.55
    addWidget
    -0.55
    鰭
    -0.54
    PyExc
    -0.53
     défend
    -0.52
    POSITIVE LOGITS
     series
    4.31
    series
    3.88
     Series
    3.88
    Series
    3.78
     SERIES
    3.70
     serie
    3.31
    SERIES
    3.28
     série
    3.19
    serie
    2.89
     séries
    2.80
    Activations Density 0.042%

    No Known Activations