© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 25666
    Prev
    Next
    INDEX
    Explanations

    intense profanity and sexual content

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    styleType
    -0.95
    وردار
    -0.75
     Trost
    -0.75
    Gale
    -0.72
    Vea
    -0.71
    ExtendWith
    -0.70
     Vela
    -0.69
    ductory
    -0.69
    GHIJKLM
    -0.68
     AdapterView
    -0.65
    POSITIVE LOGITS
    fuck
    1.34
    FUCK
    1.33
    fucker
    1.27
     shit
    1.24
     fuck
    1.23
    Fuck
    1.22
     fucked
    1.22
     Fuck
    1.20
    shit
    1.17
     SHIT
    1.17
    Activations Density 0.023%

    No Known Activations