© 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-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 5685
    Prev
    Next
    INDEX
    Explanations

    information about product conditions and quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    Not in Any Lists

    No Comments

    Negative Logits
    marshaller
    -0.61
    ContentAsync
    -0.60
     Exactos
    -0.55
    glBind
    -0.53
    exitRule
    -0.52
    BlockingQueue
    -0.52
    abestanden
    -0.51
     Sech
    -0.50
    enterOuterAlt
    -0.50
     betweenstory
    -0.48
    POSITIVE LOGITS
     scratches
    1.27
     marks
    1.12
     damage
    1.00
     wear
    0.99
     blemishes
    0.98
     dents
    0.98
     scratch
    0.97
     scratched
    0.92
     scu
    0.92
     cracks
    0.92
    Activations Density 0.196%

    No Known Activations