© 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-2-9B
    7. Residual Stream - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 11662
    Prev
    Next
    INDEX
    Explanations

    content related to charitable activities and volunteer work for people in need

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    tagext
    -0.48
    stance
    -0.43
    rawl
    -0.41
    ("~/
    -0.41
     substance
    -0.40
    riso
    -0.39
     Lerner
    -0.39
    insic
    -0.39
     realization
    -0.38
     مز
    -0.38
    POSITIVE LOGITS
     rootReducer
    0.50
     varandra
    0.43
     <=",
    0.42
     igenom
    0.41
     utveckling
    0.39
     vandens
    0.39
     laiko
    0.39
     avoient
    0.38
     setCode
    0.38
     Signalez
    0.37
    Activations Density 0.240%

    No Known Activations