© 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. 21-GEMMASCOPE-RES-16K
    11. 10346
    Prev
    Next
    INDEX
    Explanations

    patterns of evaluation regarding progress and expectations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     שוליים
    -0.47
     paraître
    -0.45
    ECONDS
    -0.40
     aplicado
    -0.39
     réaction
    -0.38
     gerekti
    -0.38
    ể
    -0.38
    scribers
    -0.37
    SerializedName
    -0.37
    Sudden
    -0.36
    POSITIVE LOGITS
    setVerticalGroup
    0.58
    TypedDataSet
    0.56
     goals
    0.54
     اهداف
    0.54
     objectives
    0.54
     objetivo
    0.53
     purpose
    0.52
     هدف
    0.50
    目的
    0.48
     doel
    0.48
    Activations Density 0.428%

    No Known Activations