© 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. 20-GEMMASCOPE-RES-16K
    11. 15139
    Prev
    Next
    INDEX
    Explanations

    references to comparisons or contrasts within the text

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

    "former" or "latter" follows "the"

    np_acts-logits-general · gemini-2.0-flash

    the former or the latter

    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
    enough
    -0.58
    ation
    -0.55
    Portail
    -0.55
     referenties
    -0.53
    Enough
    -0.53
     enough
    -0.53
    %"),
    -0.52
     Mazar
    -0.51
     nid
    -0.51
    ntgen
    -0.49
    POSITIVE LOGITS
     latter
    3.57
     former
    2.72
    latter
    2.55
    后者
    2.38
    former
    2.25
    Former
    2.18
     Former
    2.08
     senare
    1.84
     letz
    1.72
     later
    1.68
    Activations Density 0.473%

    No Known Activations