© 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. 11382
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating levels of difficulty or intensity

    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
     ISNI
    -0.63
     and
    -0.57
    Enllaços
    -0.54
    ukunft
    -0.54
    슷
    -0.54
    WebElementEntity
    -0.52
    gnore
    -0.51
    /
    -0.51
    CHOR
    -0.48
    öhne
    -0.48
    POSITIVE LOGITS
     usual
    1.22
     expected
    1.17
    kyou
    1.08
     anticipated
    1.06
     ever
    1.04
    usual
    1.03
    expected
    1.01
     anyone
    0.96
     anything
    0.94
     any
    0.89
    Activations Density 0.316%

    No Known Activations