© 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. 16-GEMMASCOPE-RES-16K
    11. 4815
    Prev
    Next
    INDEX
    Explanations

    questions and phrases inquiring about extent or quantity

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

    Comes before "much" or "hard" or "indoctr"

    np_acts-logits-general · gemini-2.0-flash

    how explained

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hjelp
    -0.59
     materiaal
    -0.56
     specchio
    -0.52
     beseech
    -0.51
     legyen
    -0.51
     borealis
    -0.51
     corretamente
    -0.51
     öner
    -0.51
     soient
    -0.50
     sanitarias
    -0.50
    POSITIVE LOGITS
    WHEREAS
    0.78
     autorytatywna
    0.74
    Aiheesta
    0.70
     how
    0.66
     चीज़ों
    0.66
    
    0.65
    ioutil
    0.64
     mergeFrom
    0.64
     much
    0.63
    ervant
    0.62
    Activations Density 0.054%

    No Known Activations