© 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. 10558
    Prev
    Next
    INDEX
    Explanations

    questions and expressions related to understanding emotions and thoughts

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

    Followed by a form of "to be"

    np_acts-logits-general · gemini-2.0-flash

    non-English present progressive

    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
     Did
    -0.55
    Did
    -0.47
     did
    -0.46
     Will
    -0.46
    >(_
    -0.43
    Would
    -0.41
     Would
    -0.41
     D
    -0.41
    la
    -0.40
    шее
    -0.40
    POSITIVE LOGITS
     đang
    1.40
     estão
    1.24
     sedang
    1.21
     estamos
    1.20
    正在
    1.15
     está
    1.15
     stanno
    1.13
     están
    1.11
     Estamos
    1.08
     estou
    1.08
    Activations Density 0.646%

    No Known Activations