© 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. 13-GEMMASCOPE-RES-65K
    11. 15504
    Prev
    Next
    INDEX
    Explanations

    the presence of the special token `<bos>`, which likely indicates the beginning of a segment or section in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ([^
    -0.84
    aktery
    -0.82
    覆
    -0.77
     Bradford
    -0.77
    xss
    -0.76
     PMS
    -0.76
     McGrath
    -0.75
    getConfiguration
    -0.74
    cila
    -0.72
    ashe
    -0.72
    POSITIVE LOGITS
     ***!
    0.96
     Roja
    0.93
    
    0.91
     Gorbachev
    0.91
     Eilish
    0.89
     Monfieur
    0.88
     Rolf
    0.87
    Tao
    0.87
     tann
    0.86
     sap
    0.84
    Activations Density 0.076%

    No Known Activations