© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 15424
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cause" and its variations, indicating a focus on causality and effects

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

    "Cause" or "caused" followed by a word

    np_acts-logits-general · gemini-2.0-flash

    cause or caused by

    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
    verständlich
    -0.70
    EndInit
    -0.68
    Autoritní
    -0.67
     للمعارف
    -0.67
     كومونز
    -0.66
    httphttps
    -0.65
    NOPQRST
    -0.63
    AsUp
    -0.62
    Referanser
    -0.61
     EconPapers
    -0.59
    POSITIVE LOGITS
     Causes
    0.91
     CAUSE
    0.90
     Cause
    0.84
     havoc
    0.82
    causes
    0.82
    caused
    0.80
     causes
    0.80
     Caus
    0.79
     cause
    0.79
     caused
    0.78
    Activations Density 0.107%

    No Known Activations