© 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. 14878
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "with" indicating relationships or associations

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

    Follows the word "with"

    np_acts-logits-general · gemini-2.0-flash

    with the / regard / respect

    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
     Cæsar
    -0.77
     Shaksp
    -0.73
     Huguen
    -0.71
     Shakspeare
    -0.70
     Charlemagne
    -0.68
     Tacitus
    -0.65
     Sarm
    -0.63
     Euripides
    -0.62
     Manchuria
    -0.61
     Upan
    -0.61
    POSITIVE LOGITS
     the
    1.28
     regards
    1.12
     regard
    1.11
     a
    1.01
     an
    0.98
    stood
    0.90
    standing
    0.88
     whom
    0.85
     respect
    0.83
    drawing
    0.82
    Activations Density 0.403%

    No Known Activations