© 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. 22-GEMMASCOPE-RES-16K
    11. 4871
    Prev
    Next
    INDEX
    Explanations

    instances and expressions of clarity and precision in descriptions or statements

    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
     Robots
    -0.53
     Mousse
    -0.52
    ditionally
    -0.52
     endTime
    -0.50
    onson
    -0.50
    addNode
    -0.50
     Rabbits
    -0.50
     horseback
    -0.49
    Getenv
    -0.49
    ragamo
    -0.49
    POSITIVE LOGITS
     Clear
    1.07
    Clear
    1.05
     clear
    1.02
    clear
    0.99
     CLEAR
    0.96
     clears
    0.88
    CLEAR
    0.87
     Klar
    0.81
     clearing
    0.77
     clearness
    0.77
    Activations Density 0.166%

    No Known Activations