© 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. 18-GEMMASCOPE-RES-16K
    11. 3956
    Prev
    Next
    INDEX
    Explanations

    references to geographic regions or directions

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

    Directional regions paired with locations

    np_acts-logits-general · gemini-2.0-flash

    compass directions and regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.83
     antemano
    -0.65
    reportWebVitals
    -0.63
     Normdatei
    -0.60
    AccessorTable
    -0.59
     réaction
    -0.59
     leprosy
    -0.58
    kegaard
    -0.58
    nologue
    -0.57
     Ahead
    -0.57
    POSITIVE LOGITS
    ized
    0.97
    most
    0.91
    ization
    0.89
     Hemisphere
    0.77
     hemisphere
    0.76
    "):
    0.73
    MOST
    0.72
    izing
    0.71
    izer
    0.69
    ize
    0.66
    Activations Density 0.087%

    No Known Activations