© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 9855
    Prev
    Next
    INDEX
    Explanations

    various forms of rows and their attributes in HTML or CSV formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Prote
    -0.56
     Gifford
    -0.51
     Fant
    -0.51
    anticipated
    -0.50
    codename
    -0.49
     Bonner
    -0.49
    considerable
    -0.49
     Sanford
    -0.49
    sustain
    -0.48
    brief
    -0.48
    POSITIVE LOGITS
    Row
    2.11
     row
    2.05
     Row
    2.02
    row
    1.91
     rows
    1.76
     Rows
    1.72
     ROW
    1.65
    ROW
    1.64
    Rows
    1.57
    rows
    1.52
    Activations Density 0.057%

    No Known Activations