© 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. 11312
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditions and limitations in a discussion or argument

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

    Follows question mark "Q" used for questions

    np_acts-logits-general · gemini-2.0-flash

    also

    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
    Either
    -1.11
    either
    -1.10
     Either
    -1.05
     entweder
    -1.00
     either
    -1.00
     zwar
    -0.98
    จึง
    -0.96
     indeed
    -0.91
     certes
    -0.88
     efectivamente
    -0.88
    POSITIVE LOGITS
    还会
    0.61
    他还
    0.57
     וגם
    0.56
    还
    0.56
    还有一
    0.56
     other
    0.56
    顺便
    0.55
    我还
    0.54
    何より
    0.54
    还有一个
    0.53
    Activations Density 0.715%

    No Known Activations