© 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. 10-GEMMASCOPE-RES-16K
    11. 16126
    Prev
    Next
    INDEX
    Explanations

    occurrences of boolean return values in conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lo
    -0.51
     online
    -0.46
    credited
    -0.43
    online
    -0.42
     pin
    -0.42
    ll
    -0.41
     Lo
    -0.41
     fast
    -0.41
    оте
    -0.40
    Fi
    -0.39
    POSITIVE LOGITS
     Efq
    0.95
     myſelf
    0.94
     للاسماء
    0.92
     snippetHide
    0.92
     Theſe
    0.92
     itſelf
    0.90
    RetentionPolicy
    0.89
     pleaſure
    0.88
     endwhile
    0.88
     Jefus
    0.87
    Activations Density 0.084%

    No Known Activations