© 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. 21-GEMMASCOPE-RES-16K
    11. 14595
    Prev
    Next
    INDEX
    Explanations

    scripting or programming language syntax, particularly conditionals and statements

    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
     Subsequent
    -0.75
     Later
    -0.75
    Later
    -0.73
    Eventually
    -0.62
     Eventually
    -0.61
    sequent
    -0.59
     subsequent
    -0.59
    Afterwards
    -0.58
     Afterwards
    -0.55
     followed
    -0.52
    POSITIVE LOGITS
     then
    1.34
     então
    1.29
     allora
    1.15
     entonces
    1.07
     alors
    1.07
     atunci
    1.04
     Alors
    1.04
    Então
    0.98
    Alors
    0.97
    אז
    0.92
    Activations Density 0.196%

    No Known Activations