© 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 - 16k
    9. 6-GEMMASCOPE-RES-16K
    11. 4180
    Prev
    Next
    INDEX
    Explanations

    references to information or data descriptors

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Walkover
    -0.81
    isEqualTo
    -0.76
     Rasmussen
    -0.74
    gatsby
    -0.69
     Marra
    -0.69
    trische
    -0.68
     Daven
    -0.67
    guen
    -0.67
     Searle
    -0.67
     Ras
    -0.66
    POSITIVE LOGITS
     Info
    1.53
    Info
    1.47
    info
    1.47
     info
    1.40
    INFO
    1.36
     infos
    1.36
     getInfo
    1.31
     INFO
    1.26
    infos
    1.22
    ginfo
    1.16
    Activations Density 0.034%

    No Known Activations