© 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. 25-GEMMASCOPE-RES-16K
    11. 16229
    Prev
    Next
    INDEX
    Explanations

    references to individuals and legal cases

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    led
    -0.82
    le
    -0.82
    let
    -0.79
    la
    -0.76
    late
    -0.70
    les
    -0.66
    ly
    -0.65
    leta
    -0.63
    li
    -0.62
    len
    -0.61
    POSITIVE LOGITS
     RL
    0.66
     Ll
    0.65
     LL
    0.65
     Л
    0.57
     Lí
    0.55
    RL
    0.55
     LM
    0.55
     LQ
    0.54
     LH
    0.54
     Լ
    0.52
    Activations Density 1.655%

    No Known Activations