© 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. 22-GEMMASCOPE-RES-16K
    11. 2842
    Prev
    Next
    INDEX
    Explanations

    references to varying opinions or numbers of people

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

    Comes before a verb

    np_acts-logits-general · gemini-2.0-flash

    commencing with some

    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
     respectively
    -0.54
    一个个
    -0.52
    respectively
    -0.49
    }*/
    -0.48
    分别
    -0.47
     niya
    -0.47
     jeweiligen
    -0.47
     وهم
    -0.46
    moveToFirst
    -0.45
    themselves
    -0.45
    POSITIVE LOGITS
     people
    1.21
     times
    0.89
     folks
    0.88
    Portale
    0.84
     commentators
    0.80
    people
    0.80
     jurisdictions
    0.78
     thinks
    0.77
     <<<<<<<<<<<<<<
    0.76
     things
    0.76
    Activations Density 0.203%

    No Known Activations