© 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-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 1424
    Prev
    Next
    INDEX
    Explanations

    elements related to feedback and assessments in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    growing
    -0.56
     growing
    -0.55
     grows
    -0.54
     evolves
    -0.50
     begins
    -0.49
    
    -0.49
     increasingly
    -0.48
    ActiveRecord
    -0.48
     handleMessage
    -0.47
    ρκ
    -0.47
    POSITIVE LOGITS
     did
    1.46
     took
    1.33
     was
    1.29
     went
    1.28
    did
    1.24
     Did
    1.20
    Did
    1.18
     gave
    1.17
     happened
    1.12
     didn
    1.10
    Activations Density 1.134%

    No Known Activations