© 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. 22-GEMMASCOPE-RES-16K
    11. 10643
    Prev
    Next
    INDEX
    Explanations

    phrases related to administrative procedures and filings

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

    Follows determiners ("the", "a", "his")

    np_acts-logits-general · gemini-2.0-flash

    full profit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Schwert
    -0.54
     dizi
    -0.53
     varandra
    -0.51
     habet
    -0.49
     begy
    -0.48
    zeptember
    -0.48
     käns
    -0.47
     étoit
    -0.47
     africaine
    -0.47
     picioare
    -0.47
    POSITIVE LOGITS
    tagHelperRunner
    0.80
     intimated
    0.75
     désolés
    0.75
    webElement
    0.75
     متعلقه
    0.73
    Contd
    0.69
     pinulongan
    0.67
     corrig
    0.66
     '{@
    0.63
     Signalez
    0.62
    Activations Density 0.063%

    No Known Activations