© 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. 18-GEMMASCOPE-RES-16K
    11. 1910
    Prev
    Next
    INDEX
    Explanations

    instances of personal relationships and emotional connections

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

    Preceding people's names, often at the start of a sentence

    np_acts-logits-general · gemini-2.0-flash

    narrative turns and discoveries

    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
     avoient
    -0.83
     habet
    -0.81
     étoit
    -0.78
     pouvoit
    -0.76
     étoient
    -0.74
     <<<<<<<<<<<<<<
    -0.73
     auroit
    -0.73
     ſeveral
    -0.70
     mérit
    -0.69
     aiment
    -0.69
    POSITIVE LOGITS
     became
    0.92
     become
    0.85
     becomes
    0.81
     began
    0.74
     suddenly
    0.71
     discovered
    0.66
     unexpectedly
    0.65
     mulai
    0.61
     finally
    0.61
     becoming
    0.59
    Activations Density 0.527%

    No Known Activations