© 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. 2-GEMMASCOPE-RES-16K
    11. 16051
    Prev
    Next
    INDEX
    Explanations

    instances of disorganization or confusion in context

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     AssemblyCulture
    -0.50
    DeleteBehavior
    -0.49
    CancelButton
    -0.41
     lucky
    -0.40
    BaseType
    -0.40
     Lucky
    -0.40
    Syl
    -0.40
    LSB
    -0.40
    зда
    -0.39
    keta
    -0.39
    POSITIVE LOGITS
    dump
    0.83
     dump
    0.81
     Mes
    0.81
    Mes
    0.80
     mess
    0.77
     mes
    0.77
     transcript
    0.77
    Dump
    0.75
     Dump
    0.73
     Mess
    0.73
    Activations Density 0.606%

    No Known Activations