© 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. 16174
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relationships and personal connections

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

    preceding verbs (often "to")

    np_acts-logits-general · gemini-2.0-flash

    active movement verbs

    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
    ſelf
    -0.60
     avoit
    -0.56
     quæ
    -0.56
     feroit
    -0.56
     librement
    -0.53
     pouvoit
    -0.53
     étoit
    -0.52
     dům
    -0.52
    conceito
    -0.52
     quelquefois
    -0.52
    POSITIVE LOGITS
     trot
    0.78
     jumped
    0.76
     merrily
    0.76
     unleash
    0.74
     swoop
    0.74
     hopped
    0.72
     popped
    0.70
     leapt
    0.69
     jump
    0.68
     echar
    0.68
    Activations Density 0.511%

    No Known Activations