© 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. 5477
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a continuation or pause in dialogue

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

    Tokens following ellipses ("…")

    np_acts-logits-general · gemini-2.0-flash

    specific technical terms

    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
    ành
    -0.67
    ISupport
    -0.63
    foot
    -0.62
    Activités
    -0.60
     Schnee
    -0.60
     pubb
    -0.60
     Slee
    -0.59
     coper
    -0.58
     Moderato
    -0.58
     Bär
    -0.57
    POSITIVE LOGITS
    存于互联网档案馆
    0.90
     للمعارف
    0.79
    RenderAtEndOf
    0.79
     ProtoMessage
    0.77
     كومونز
    0.75
    PYX
    0.74
    VIAF
    0.73
    ]:
    0.73
    DataSetChanged
    0.73
    出版年
    0.72
    Activations Density 0.372%

    No Known Activations