© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 354
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditional logic and error handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Conditional logic or control flow

    np_acts-logits-general · gemini-2.0-flash

    conditional completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     interrelated
    -0.54
    httphttps
    -0.51
    rams
    -0.47
    vailable
    -0.47
     Senin
    -0.47
    lizing
    -0.46
    owatt
    -0.46
     compos
    -0.46
    surate
    -0.46
    predict
    -0.45
    POSITIVE LOGITS
     return
    0.86
    fromnode
    0.79
     proceed
    0.78
     continue
    0.73
     propOrder
    0.69
     skip
    0.68
     PROCEED
    0.68
    proceed
    0.68
     CONTINUE
    0.66
     dianggap
    0.65
    Activations Density 0.482%

    No Known Activations