© 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 - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 17725
    Prev
    Next
    INDEX
    Explanations

    initialization or configuration markers in structured documents

    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
     تانيه
    -1.31
     XNUMX
    -1.22
     Majefty
    -1.20
     iſt
    -1.20
    WriteBarrier
    -1.15
     itſelf
    -1.10
     myſelf
    -1.06
     Dase
    -1.05
     fhort
    -1.05
    出版年
    -1.05
    POSITIVE LOGITS
     tbl
    0.91
     Til
    0.76
     til
    0.74
    tbl
    0.71
    Til
    0.69
     kwa
    0.67
     Kwa
    0.66
    msgSender
    0.66
     Voor
    0.66
    YL
    0.66
    Activations Density 0.020%

    No Known Activations