© 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. 8140
    Prev
    Next
    INDEX
    Explanations

    concepts related to healing and overcoming challenges

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

    after verbs suggesting removal or prevention

    np_acts-logits-general · gemini-2.0-flash

    getting rid of unwanted things

    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
    rungsseite
    -0.81
     noDo
    -0.68
    Tikang
    -0.67
    ⓧ
    -0.67
    /*
    -0.66
     تضيفلها
    -0.66
    writeFieldEnd
    -0.66
     OnTrigger
    -0.64
     OFDb
    -0.63
     насељу
    -0.62
    POSITIVE LOGITS
     unwanted
    0.87
     excess
    0.78
     misconceptions
    0.77
     excesses
    0.76
     pesky
    0.76
    excess
    0.74
     harmful
    0.71
     stubborn
    0.68
     worries
    0.67
     fears
    0.66
    Activations Density 0.599%

    No Known Activations