© 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. 6110
    Prev
    Next
    INDEX
    Explanations

    numerical values and mathematical operators

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

    The number 8

    np_acts-logits-general · gemini-2.0-flash

    eight and sixteen

    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
    Personendaten
    -0.66
    Autoritní
    -0.62
    fromnode
    -0.62
     continúas
    -0.60
     Orrell
    -0.60
    AndEndTag
    -0.56
     mariée
    -0.56
     contextLoads
    -0.55
     répondit
    -0.54
     تضيفلها
    -0.54
    POSITIVE LOGITS
     eight
    0.94
     Eight
    0.81
     sixteen
    0.80
    8
    0.79
    eight
    0.77
     ocho
    0.72
    Eight
    0.66
     eighth
    0.65
     EIGHT
    0.64
     Eighth
    0.59
    Activations Density 0.858%

    No Known Activations