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

    Neuronpedia

    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. 22-GEMMASCOPE-RES-16K
    11. 6642
    Prev
    Next
    INDEX
    Explanations

    individuals' reflections on their personal journeys and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forward
    -0.39
     forward
    -0.38
     Rub
    -0.37
    loxy
    -0.37
     OH
    -0.37
    rub
    -0.36
     Hand
    -0.36
     Posi
    -0.36
    laken
    -0.35
    室
    -0.35
    POSITIVE LOGITS
     hometown
    0.70
     homecoming
    0.68
     AssemblyTitle
    0.67
     homeland
    0.65
     tė
    0.62
    AddTagHelper
    0.58
     aunts
    0.58
     Rückkehr
    0.57
     boyhood
    0.56
     relatives
    0.55
    Activations Density 0.302%

    No Known Activations