© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 3902
    Prev
    Next
    INDEX
    Explanations

    references to citations or footnotes within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.59
    <eos>
    -0.54
    ↵
    -0.51
     The
    -0.48
    ↵↵↵
    -0.45
      
    -0.44
    </h2>
    -0.43
     I
    -0.42
     Tab
    -0.41
     tra
    -0.40
    POSITIVE LOGITS
     AssemblyCulture
    1.00
     propOrder
    0.93
     виправивши
    0.90
    fjspx
    0.90
    berdayakan
    0.81
     MainAxisSize
    0.81
     resourceCulture
    0.79
    awtextra
    0.79
    Personensuche
    0.78
     GenerationType
    0.77
    Activations Density 0.350%

    No Known Activations